Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1221. Min Range: -5.1221
Max Act: 5.1221. Min Act: -0.1700
Data Index: 4113364 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1221. Min Range: -5.1221
Max Act: 5.0284. Min Act: -0.1700
Data Index: 8790873 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1221. Min Range: -5.1221
Max Act: 5.0284. Min Act: -0.1700
Data Index: 6227194 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1221. Min Range: -5.1221
Max Act: 5.0284. Min Act: -0.1700
Data Index: 1873965 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9971. Min Act: -0.1700
Data Index: 6024678 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9971. Min Act: -0.1700
Data Index: 7563962 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9659. Min Act: -0.1700
Data Index: 5840474 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9659. Min Act: -0.1700
Data Index: 8569593 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9659. Min Act: -0.1700
Data Index: 8569592 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9659. Min Act: -0.1700
Data Index: 892279 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9346. Min Act: -0.1700
Data Index: 6161663 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9034. Min Act: -0.1700
Data Index: 8167506 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9034. Min Act: -0.1700
Data Index: 7885855 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9034. Min Act: -0.1700
Data Index: 357626 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.8721. Min Act: -0.1700
Data Index: 1685495 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9034. Min Act: -0.1700
Data Index: 7710424 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.9034. Min Act: -0.1700
Data Index: 7775161 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.8721. Min Act: -0.1700
Data Index: 2104547 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.8721. Min Act: -0.1700
Data Index: 4820813 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1221. Min Range: -5.1221
Max Act: 4.8721. Min Act: -0.1700
Data Index: 5124795 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19