Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.4714. Min Act: -0.1700
Data Index: 2547959 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.1589. Min Act: -0.1700
Data Index: 365697 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2214. Min Act: -0.1700
Data Index: 1984998 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.0964. Min Act: -0.1700
Data Index: 6246761 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.0652. Min Act: -0.1700
Data Index: 4738254 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.9714. Min Act: -0.1700
Data Index: 7866326 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.9714. Min Act: -0.1700
Data Index: 3301610 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.0027. Min Act: -0.1700
Data Index: 5654170 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.9714. Min Act: -0.1700
Data Index: 1511512 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.9714. Min Act: -0.1700
Data Index: 5061482 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.9714. Min Act: -0.1700
Data Index: 5289336 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.9089. Min Act: -0.1700
Data Index: 1859855 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8777. Min Act: -0.1700
Data Index: 8176578 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8777. Min Act: -0.1700
Data Index: 204750 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8777. Min Act: -0.1700
Data Index: 7278610 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8777. Min Act: -0.1700
Data Index: 7515923 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8464. Min Act: -0.1700
Data Index: 7501837 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8152. Min Act: -0.1700
Data Index: 3463614 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8152. Min Act: -0.1700
Data Index: 2356452 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4714. Min Range: -5.4714
Max Act: 4.8152. Min Act: -0.1700
Data Index: 6238316 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19