Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4331 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.7791. Min Act: -0.1700
Data Index: 471066 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.6541. Min Act: -0.1700
Data Index: 7214316 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.5916. Min Act: -0.1700
Data Index: 1186067 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.4978. Min Act: -0.1700
Data Index: 8524398 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.4353. Min Act: -0.1700
Data Index: 7456042 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.4041. Min Act: -0.1700
Data Index: 6561317 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.4041. Min Act: -0.1700
Data Index: 7733448 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.4041. Min Act: -0.1700
Data Index: 7095695 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.3416. Min Act: -0.1700
Data Index: 7362335 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.3103. Min Act: -0.1700
Data Index: 8707768 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.3103. Min Act: -0.1700
Data Index: 8060584 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2791. Min Act: -0.1700
Data Index: 4960544 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2791. Min Act: -0.1700
Data Index: 4113085 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2478. Min Act: -0.1700
Data Index: 3856880 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2478. Min Act: -0.1700
Data Index: 3582663 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2478. Min Act: -0.1700
Data Index: 7947519 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2166. Min Act: -0.1700
Data Index: 6561712 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.1853. Min Act: -0.1700
Data Index: 3078015 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.2166. Min Act: -0.1700
Data Index: 4452200 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7791. Min Range: -6.7791
Max Act: 6.1853. Min Act: -0.1700
Data Index: 4148183 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19