Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3120. Min Range: -7.3120
Max Act: 7.3120. Min Act: -0.1700
Data Index: 1759322 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.8120. Min Act: -0.1700
Data Index: 5497858 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.7495. Min Act: -0.1700
Data Index: 1064428 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.7495. Min Act: -0.1700
Data Index: 2368224 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.7182. Min Act: -0.1700
Data Index: 1334115 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.6557. Min Act: -0.1700
Data Index: 980161 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.5932. Min Act: -0.1700
Data Index: 7688175 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.5620. Min Act: -0.1700
Data Index: 8690007 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.5307. Min Act: -0.1700
Data Index: 7158178 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4995. Min Act: -0.1700
Data Index: 3130996 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4682. Min Act: -0.1700
Data Index: 95736 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4682. Min Act: -0.1700
Data Index: 202821 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4370. Min Act: -0.1700
Data Index: 7184998 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4057. Min Act: -0.1700
Data Index: 654110 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4370. Min Act: -0.1700
Data Index: 5818240 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4370. Min Act: -0.1700
Data Index: 4399555 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4370. Min Act: -0.1700
Data Index: 5608966 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.4057. Min Act: -0.1700
Data Index: 542325 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.3745. Min Act: -0.1700
Data Index: 6983742 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3120. Min Range: -7.3120
Max Act: 6.3432. Min Act: -0.1700
Data Index: 3233523 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19