Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.8191. Min Act: -0.1700
Data Index: 8771688 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.6941. Min Act: -0.1700
Data Index: 1161152 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.6628. Min Act: -0.1700
Data Index: 7328826 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.6316. Min Act: -0.1700
Data Index: 8547327 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.5691. Min Act: -0.1700
Data Index: 2368267 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.5378. Min Act: -0.1700
Data Index: 5339364 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.5691. Min Act: -0.1700
Data Index: 1539704 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.5378. Min Act: -0.1700
Data Index: 7137885 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.5378. Min Act: -0.1700
Data Index: 8027912 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.4441. Min Act: -0.1700
Data Index: 8564397 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.4441. Min Act: -0.1700
Data Index: 8649669 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.4128. Min Act: -0.1700
Data Index: 2483276 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.4128. Min Act: -0.1700
Data Index: 3126669 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.4128. Min Act: -0.1700
Data Index: 4354912 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1078533 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.3816. Min Act: -0.1700
Data Index: 8156164 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.3816. Min Act: -0.1700
Data Index: 2831302 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.3503. Min Act: -0.1700
Data Index: 1784387 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.3503. Min Act: -0.1700
Data Index: 5450226 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8191. Min Range: -6.8191
Max Act: 6.3503. Min Act: -0.1700
Data Index: 4744488 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19