Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.8064. Min Act: -0.1700
Data Index: 7637810 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.6189. Min Act: -0.1700
Data Index: 7445428 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.5564. Min Act: -0.1700
Data Index: 1941131 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.4939. Min Act: -0.1700
Data Index: 365302 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.4002. Min Act: -0.1700
Data Index: 350517 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.3689. Min Act: -0.1700
Data Index: 8545299 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.3064. Min Act: -0.1700
Data Index: 5847364 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.3377. Min Act: -0.1700
Data Index: 2924136 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.3064. Min Act: -0.1700
Data Index: 8593898 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.2752. Min Act: -0.1700
Data Index: 8380245 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.2752. Min Act: -0.1700
Data Index: 8116465 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.2752. Min Act: -0.1700
Data Index: 3957302 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.2439. Min Act: -0.1700
Data Index: 8830181 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1814. Min Act: -0.1700
Data Index: 833557 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1814. Min Act: -0.1700
Data Index: 4231399 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1814. Min Act: -0.1700
Data Index: 3093168 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1814. Min Act: -0.1700
Data Index: 1752574 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1814. Min Act: -0.1700
Data Index: 2672659 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1502. Min Act: -0.1700
Data Index: 5577670 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8064. Min Range: -6.8064
Max Act: 6.1189. Min Act: -0.1700
Data Index: 4948199 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19