Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 541633 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 6499229 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 3389612 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7323. Min Act: -0.1700
Data Index: 2979390 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7011. Min Act: -0.1700
Data Index: 5414193 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7011. Min Act: -0.1700
Data Index: 700808 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7011. Min Act: -0.1700
Data Index: 3079206 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.7011. Min Act: -0.1700
Data Index: 649620 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6698. Min Act: -0.1700
Data Index: 45504 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6698. Min Act: -0.1700
Data Index: 596837 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6385. Min Act: -0.1700
Data Index: 277818 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6385. Min Act: -0.1700
Data Index: 8349309 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6385. Min Act: -0.1700
Data Index: 5879955 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.5760. Min Act: -0.1700
Data Index: 4769731 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6073. Min Act: -0.1700
Data Index: 2257228 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6073. Min Act: -0.1700
Data Index: 549836 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.6073. Min Act: -0.1700
Data Index: 756446 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.5760. Min Act: -0.1700
Data Index: 4431699 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.5760. Min Act: -0.1700
Data Index: 4920101 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7636. Min Range: -4.7636
Max Act: 4.5760. Min Act: -0.1700
Data Index: 5158952 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19