Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0008. Min Range: -5.0008
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4625975 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.5320. Min Act: -0.1700
Data Index: 4292338 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.5320. Min Act: -0.1700
Data Index: 5988077 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.5008. Min Act: -0.1700
Data Index: 8050806 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.4695. Min Act: -0.1700
Data Index: 8621809 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.4695. Min Act: -0.1700
Data Index: 8696097 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.4383. Min Act: -0.1700
Data Index: 5041491 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5280595 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3758. Min Act: -0.1700
Data Index: 7236524 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3758. Min Act: -0.1700
Data Index: 2719120 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3445. Min Act: -0.1700
Data Index: 8603674 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3445. Min Act: -0.1700
Data Index: 979383 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3445. Min Act: -0.1700
Data Index: 8663685 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3445. Min Act: -0.1700
Data Index: 1815110 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.3133. Min Act: -0.1700
Data Index: 189204 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.2820. Min Act: -0.1700
Data Index: 1311773 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.2508. Min Act: -0.1700
Data Index: 5918369 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.2508. Min Act: -0.1700
Data Index: 1739308 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.2508. Min Act: -0.1700
Data Index: 7015082 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0008. Min Range: -5.0008
Max Act: 4.2508. Min Act: -0.1700
Data Index: 2114527 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19