Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.3603. Min Act: -0.1700
Data Index: 1835107 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.3603. Min Act: -0.1700
Data Index: 7604493 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.3291. Min Act: -0.1700
Data Index: 1104557 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.3291. Min Act: -0.1700
Data Index: 3509821 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.2978. Min Act: -0.1700
Data Index: 8244077 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.2666. Min Act: -0.1700
Data Index: 2043200 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.2041. Min Act: -0.1700
Data Index: 84091 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1728. Min Act: -0.1700
Data Index: 4519503 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1416. Min Act: -0.1700
Data Index: 3049093 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1103. Min Act: -0.1700
Data Index: 8089332 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1416. Min Act: -0.1700
Data Index: 1712013 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1416. Min Act: -0.1700
Data Index: 8745477 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1416. Min Act: -0.1700
Data Index: 6841220 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1103. Min Act: -0.1700
Data Index: 2586000 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1416. Min Act: -0.1700
Data Index: 8451511 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.1103. Min Act: -0.1700
Data Index: 3216794 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.0791. Min Act: -0.1700
Data Index: 1040101 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.0791. Min Act: -0.1700
Data Index: 5835698 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.0791. Min Act: -0.1700
Data Index: 697253 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3603. Min Range: -5.3603
Max Act: 5.0791. Min Act: -0.1700
Data Index: 1971343 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19