Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.9728. Min Act: -0.1700
Data Index: 1993503 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.7228. Min Act: -0.1700
Data Index: 6701878 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.5353. Min Act: -0.1700
Data Index: 505633 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.4728. Min Act: -0.1700
Data Index: 4983479 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.4728. Min Act: -0.1700
Data Index: 2260142 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.3478. Min Act: -0.1700
Data Index: 3232587 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.2853. Min Act: -0.1700
Data Index: 1033870 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.2228. Min Act: -0.1700
Data Index: 5098671 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.2228. Min Act: -0.1700
Data Index: 5623276 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.2228. Min Act: -0.1700
Data Index: 7786032 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.1603. Min Act: -0.1700
Data Index: 6457660 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.1603. Min Act: -0.1700
Data Index: 3920215 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.1603. Min Act: -0.1700
Data Index: 7599480 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.1603. Min Act: -0.1700
Data Index: 7194833 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.2228. Min Act: -0.1700
Data Index: 8742193 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.1603. Min Act: -0.1700
Data Index: 1653064 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.1603. Min Act: -0.1700
Data Index: 3218994 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.0978. Min Act: -0.1700
Data Index: 816215 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.0978. Min Act: -0.1700
Data Index: 2531046 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9728. Min Range: -8.9728
Max Act: 8.0978. Min Act: -0.1700
Data Index: 4622363 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19