Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6173 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1476. Min Range: -5.1476
Max Act: 5.1476. Min Act: -0.1700
Data Index: 2242935 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.9601. Min Act: -0.1700
Data Index: 8472111 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.8976. Min Act: -0.1700
Data Index: 8368143 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.8351. Min Act: -0.1700
Data Index: 8019262 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.8039. Min Act: -0.1700
Data Index: 7298403 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.7726. Min Act: -0.1700
Data Index: 8748878 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.7414. Min Act: -0.1700
Data Index: 4810269 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.7414. Min Act: -0.1700
Data Index: 4119483 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.7414. Min Act: -0.1700
Data Index: 627153 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.7101. Min Act: -0.1700
Data Index: 3372672 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.7101. Min Act: -0.1700
Data Index: 7834851 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.6789. Min Act: -0.1700
Data Index: 1454901 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 3061657 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 4499752 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.6476. Min Act: -0.1700
Data Index: 3843606 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.6164. Min Act: -0.1700
Data Index: 2395209 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.6164. Min Act: -0.1700
Data Index: 7643988 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.5851. Min Act: -0.1700
Data Index: 7874849 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.5851. Min Act: -0.1700
Data Index: 5370026 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1476. Min Range: -5.1476
Max Act: 4.5539. Min Act: -0.1700
Data Index: 4447863 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19