Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2094. Min Range: -6.2094
Max Act: 6.2094. Min Act: -0.1700
Data Index: 2412606 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.9282. Min Act: -0.1700
Data Index: 571817 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.8344. Min Act: -0.1700
Data Index: 3985076 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.8032. Min Act: -0.1700
Data Index: 1987383 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5471622 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.7094. Min Act: -0.1700
Data Index: 1818267 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.6469. Min Act: -0.1700
Data Index: 6076379 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.6157. Min Act: -0.1700
Data Index: 4168220 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5844. Min Act: -0.1700
Data Index: 1006154 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5532. Min Act: -0.1700
Data Index: 3445164 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5532. Min Act: -0.1700
Data Index: 2743453 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5532. Min Act: -0.1700
Data Index: 5210550 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5532. Min Act: -0.1700
Data Index: 129654 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.4907. Min Act: -0.1700
Data Index: 6796717 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5219. Min Act: -0.1700
Data Index: 7752026 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.5219. Min Act: -0.1700
Data Index: 3348859 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.4907. Min Act: -0.1700
Data Index: 4485975 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.4907. Min Act: -0.1700
Data Index: 3140253 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.4594. Min Act: -0.1700
Data Index: 415465 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2094. Min Range: -6.2094
Max Act: 5.4594. Min Act: -0.1700
Data Index: 1930577 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19