Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4349 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1886. Min Range: -11.1886
Max Act: 11.1886. Min Act: -0.1700
Data Index: 566182 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1886. Min Range: -11.1886
Max Act: 11.1261. Min Act: -0.1700
Data Index: 2920576 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1886. Min Range: -11.1886
Max Act: 11.0636. Min Act: -0.1700
Data Index: 606691 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1886. Min Range: -11.1886
Max Act: 11.0011. Min Act: -0.1700
Data Index: 3091397 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.8761. Min Act: -0.1700
Data Index: 88727 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.9386. Min Act: -0.1700
Data Index: 2920575 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.8761. Min Act: -0.1700
Data Index: 3805587 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.8761. Min Act: -0.1700
Data Index: 2372961 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.8761. Min Act: -0.1700
Data Index: 3284004 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.8136. Min Act: -0.1700
Data Index: 4958431 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.8136. Min Act: -0.1700
Data Index: 938625 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.7511. Min Act: -0.1700
Data Index: 3401958 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.7511. Min Act: -0.1700
Data Index: 7522507 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 292940 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 7522510 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 5441843 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 5423807 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 5010869 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 357938 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1886. Min Range: -11.1886
Max Act: 10.6886. Min Act: -0.1700
Data Index: 193186 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19