Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.6598. Min Act: -0.1700
Data Index: 8619158 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.3473. Min Act: -0.1700
Data Index: 5779073 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.3161. Min Act: -0.1700
Data Index: 5639045 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.2223. Min Act: -0.1700
Data Index: 6274391 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1911. Min Act: -0.1700
Data Index: 1571421 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1911. Min Act: -0.1700
Data Index: 7947107 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.2223. Min Act: -0.1700
Data Index: 400486 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1911. Min Act: -0.1700
Data Index: 6972857 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1598. Min Act: -0.1700
Data Index: 7164535 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1598. Min Act: -0.1700
Data Index: 3297851 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1598. Min Act: -0.1700
Data Index: 8550225 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1285. Min Act: -0.1700
Data Index: 516990 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1285. Min Act: -0.1700
Data Index: 3454802 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1285. Min Act: -0.1700
Data Index: 7849624 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.1285. Min Act: -0.1700
Data Index: 1892038 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.0973. Min Act: -0.1700
Data Index: 8141805 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.0973. Min Act: -0.1700
Data Index: 610210 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.0973. Min Act: -0.1700
Data Index: 98560 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.0973. Min Act: -0.1700
Data Index: 1873851 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6598. Min Range: -4.6598
Max Act: 4.0973. Min Act: -0.1700
Data Index: 841381 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19