Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.6419. Min Act: -0.1700
Data Index: 1719876 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.6106. Min Act: -0.1700
Data Index: 989033 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.5481. Min Act: -0.1700
Data Index: 4558135 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.5169. Min Act: -0.1700
Data Index: 7195791 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.4544. Min Act: -0.1700
Data Index: 645774 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.4544. Min Act: -0.1700
Data Index: 598382 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.4544. Min Act: -0.1700
Data Index: 1762955 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.4231. Min Act: -0.1700
Data Index: 4772733 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.4231. Min Act: -0.1700
Data Index: 3693959 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3919. Min Act: -0.1700
Data Index: 8289024 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3919. Min Act: -0.1700
Data Index: 8318578 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3919. Min Act: -0.1700
Data Index: 7729893 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3919. Min Act: -0.1700
Data Index: 4675379 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3294. Min Act: -0.1700
Data Index: 68173 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3606. Min Act: -0.1700
Data Index: 3312614 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3606. Min Act: -0.1700
Data Index: 6931363 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3294. Min Act: -0.1700
Data Index: 7973381 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.3294. Min Act: -0.1700
Data Index: 1224448 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.2981. Min Act: -0.1700
Data Index: 7111156 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6419. Min Range: -5.6419
Max Act: 5.2669. Min Act: -0.1700
Data Index: 6519941 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19