Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4236 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.3525. Min Act: -0.1700
Data Index: 6173295 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.3525. Min Act: -0.1700
Data Index: 6264485 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.2900. Min Act: -0.1700
Data Index: 6264481 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.1962. Min Act: -0.1700
Data Index: 6937477 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.1337. Min Act: -0.1700
Data Index: 8516081 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.0712. Min Act: -0.1700
Data Index: 6264482 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.1025. Min Act: -0.1700
Data Index: 768621 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.0400. Min Act: -0.1700
Data Index: 6288819 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.0400. Min Act: -0.1700
Data Index: 6264486 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3525. Min Range: -6.3525
Max Act: 6.0087. Min Act: -0.1700
Data Index: 3050627 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9462. Min Act: -0.1700
Data Index: 6763060 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9462. Min Act: -0.1700
Data Index: 1441586 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9462. Min Act: -0.1700
Data Index: 3216670 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9462. Min Act: -0.1700
Data Index: 1841782 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9462. Min Act: -0.1700
Data Index: 8516076 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9775. Min Act: -0.1700
Data Index: 2860988 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9150. Min Act: -0.1700
Data Index: 4629534 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9150. Min Act: -0.1700
Data Index: 3177890 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9462. Min Act: -0.1700
Data Index: 7684945 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3525. Min Range: -6.3525
Max Act: 5.9150. Min Act: -0.1700
Data Index: 7858022 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19