Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.2807. Min Act: -0.1700
Data Index: 5677068 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.0932. Min Act: -0.1700
Data Index: 924421 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.0932. Min Act: -0.1700
Data Index: 132944 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.9682. Min Act: -0.1700
Data Index: 7913379 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.0307. Min Act: -0.1700
Data Index: 8522849 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.0932. Min Act: -0.1700
Data Index: 2670671 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.0307. Min Act: -0.1700
Data Index: 2066663 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.9057. Min Act: -0.1700
Data Index: 2125668 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2807. Min Range: -9.2807
Max Act: 9.0307. Min Act: -0.1700
Data Index: 1953807 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.9682. Min Act: -0.1700
Data Index: 3769957 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.9057. Min Act: -0.1700
Data Index: 6971345 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.8432. Min Act: -0.1700
Data Index: 554866 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.7807. Min Act: -0.1700
Data Index: 358228 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.8432. Min Act: -0.1700
Data Index: 1483235 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.8432. Min Act: -0.1700
Data Index: 4250852 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.7807. Min Act: -0.1700
Data Index: 6033983 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.7807. Min Act: -0.1700
Data Index: 3001521 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.7807. Min Act: -0.1700
Data Index: 1093830 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.7807. Min Act: -0.1700
Data Index: 2321800 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2807. Min Range: -9.2807
Max Act: 8.7807. Min Act: -0.1700
Data Index: 4835323 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19