Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 13.0525. Min Range: -13.0525
Max Act: 13.0525. Min Act: -0.1700
Data Index: 4493766 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0525. Min Range: -13.0525
Max Act: 12.8650. Min Act: -0.1700
Data Index: 3647440 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0525. Min Range: -13.0525
Max Act: 12.4275. Min Act: -0.1700
Data Index: 335482 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0525. Min Range: -13.0525
Max Act: 12.3025. Min Act: -0.1700
Data Index: 1708678 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0525. Min Range: -13.0525
Max Act: 12.2400. Min Act: -0.1700
Data Index: 8279844 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0525. Min Range: -13.0525
Max Act: 12.2400. Min Act: -0.1700
Data Index: 1824681 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 2165762 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 867831 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 694264 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 4002894 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 3941611 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 3931933 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 379619 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 5677000 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9900. Min Act: -0.1700
Data Index: 4808011 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.9275. Min Act: -0.1700
Data Index: 7545081 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.8650. Min Act: -0.1700
Data Index: 4282216 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.8650. Min Act: -0.1700
Data Index: 4338668 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.8025. Min Act: -0.1700
Data Index: 2234856 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0525. Min Range: -13.0525
Max Act: 11.8650. Min Act: -0.1700
Data Index: 4307483 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19