Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.3397. Min Act: -0.1700
Data Index: 1590657 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.3397. Min Act: -0.1700
Data Index: 5259926 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.3240. Min Act: -0.1700
Data Index: 6151038 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.3083. Min Act: -0.1700
Data Index: 4899106 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2612. Min Act: -0.1700
Data Index: 4168066 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.3240. Min Act: -0.1700
Data Index: 6607197 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2769. Min Act: -0.1700
Data Index: 7074696 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2769. Min Act: -0.1700
Data Index: 8363615 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2612. Min Act: -0.1700
Data Index: 1101331 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2612. Min Act: -0.1700
Data Index: 1117063 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2769. Min Act: -0.1700
Data Index: 6201675 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2612. Min Act: -0.1700
Data Index: 332573 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2612. Min Act: -0.1700
Data Index: 6943679 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2455. Min Act: -0.1700
Data Index: 7920713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2455. Min Act: -0.1700
Data Index: 7402570 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2612. Min Act: -0.1700
Data Index: 7157690 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.1983. Min Act: -0.1700
Data Index: 6673721 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2455. Min Act: -0.1700
Data Index: 3800527 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2140. Min Act: -0.1700
Data Index: 3569917 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3397. Min Range: -3.3397
Max Act: 3.2140. Min Act: -0.1700
Data Index: 6968334 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19