Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8838. Min Act: -0.1700
Data Index: 5522717 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8838. Min Act: -0.1700
Data Index: 1179451 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8213. Min Act: -0.1700
Data Index: 1402881 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8213. Min Act: -0.1700
Data Index: 6357515 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.8213. Min Act: -0.1700
Data Index: 2328965 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7901. Min Act: -0.1700
Data Index: 1460199 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 8462362 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 5614384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 3989634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 4648376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 6269391 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 165377 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 4003822 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 2775479 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7901. Min Act: -0.1700
Data Index: 6694641 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 7550761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7588. Min Act: -0.1700
Data Index: 2056877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7276. Min Act: -0.1700
Data Index: 5809107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.7276. Min Act: -0.1700
Data Index: 2594086 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8838. Min Range: -6.8838
Max Act: 6.6963. Min Act: -0.1700
Data Index: 4061375 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19