Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5237 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0415. Min Act: -0.1700
Data Index: 6585198 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0415. Min Act: -0.1700
Data Index: 3774894 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0415. Min Act: -0.1700
Data Index: 3682139 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0415. Min Act: -0.1700
Data Index: 2405481 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0415. Min Act: -0.1700
Data Index: 1437327 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0103. Min Act: -0.1700
Data Index: 4018545 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0415. Min Range: -4.0415
Max Act: 4.0103. Min Act: -0.1700
Data Index: 6939704 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.9790. Min Act: -0.1700
Data Index: 8798508 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.9477. Min Act: -0.1700
Data Index: 4224094 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.9165. Min Act: -0.1700
Data Index: 4134873 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.9165. Min Act: -0.1700
Data Index: 6993928 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.9165. Min Act: -0.1700
Data Index: 6637063 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8539. Min Act: -0.1700
Data Index: 8060698 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8852. Min Act: -0.1700
Data Index: 3402574 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8852. Min Act: -0.1700
Data Index: 3583324 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8852. Min Act: -0.1700
Data Index: 6449174 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8539. Min Act: -0.1700
Data Index: 1808993 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8539. Min Act: -0.1700
Data Index: 2805066 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8539. Min Act: -0.1700
Data Index: 1361124 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0415. Min Range: -4.0415
Max Act: 3.8539. Min Act: -0.1700
Data Index: 1500210 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19