Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3598. Min Range: -6.3598
Max Act: 6.3598. Min Act: -0.1700
Data Index: 8539456 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3598. Min Range: -6.3598
Max Act: 6.2661. Min Act: -0.1700
Data Index: 7991316 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3598. Min Range: -6.3598
Max Act: 6.2661. Min Act: -0.1700
Data Index: 8026522 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.9223. Min Act: -0.1700
Data Index: 1715123 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.9223. Min Act: -0.1700
Data Index: 6483908 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8911. Min Act: -0.1700
Data Index: 1901322 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8598. Min Act: -0.1700
Data Index: 4692588 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8598. Min Act: -0.1700
Data Index: 2748745 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8598. Min Act: -0.1700
Data Index: 7217761 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8286. Min Act: -0.1700
Data Index: 1423715 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8286. Min Act: -0.1700
Data Index: 7143425 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.8286. Min Act: -0.1700
Data Index: 5639974 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7973. Min Act: -0.1700
Data Index: 5039632 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7973. Min Act: -0.1700
Data Index: 5639975 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7973. Min Act: -0.1700
Data Index: 3112335 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7973. Min Act: -0.1700
Data Index: 6323730 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7348. Min Act: -0.1700
Data Index: 5765093 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7661. Min Act: -0.1700
Data Index: 2413347 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7348. Min Act: -0.1700
Data Index: 2935098 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3598. Min Range: -6.3598
Max Act: 5.7661. Min Act: -0.1700
Data Index: 5113864 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19