Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.3716. Min Act: -0.1700
Data Index: 2832892 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.3403. Min Act: -0.1700
Data Index: 1529725 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.3403. Min Act: -0.1700
Data Index: 7062561 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1082544 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2778. Min Act: -0.1700
Data Index: 7489931 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2778. Min Act: -0.1700
Data Index: 1953796 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2466. Min Act: -0.1700
Data Index: 6125583 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2153. Min Act: -0.1700
Data Index: 4206146 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2153. Min Act: -0.1700
Data Index: 6251139 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2153. Min Act: -0.1700
Data Index: 3344595 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2153. Min Act: -0.1700
Data Index: 8565659 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2153. Min Act: -0.1700
Data Index: 7335503 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1841. Min Act: -0.1700
Data Index: 5689484 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1841. Min Act: -0.1700
Data Index: 5771391 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.2153. Min Act: -0.1700
Data Index: 7342015 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1841. Min Act: -0.1700
Data Index: 3790999 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1841. Min Act: -0.1700
Data Index: 6329669 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1841. Min Act: -0.1700
Data Index: 5426265 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1841. Min Act: -0.1700
Data Index: 2133366 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3716. Min Range: -4.3716
Max Act: 4.1216. Min Act: -0.1700
Data Index: 53707 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19