Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5917 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.9043. Min Act: -0.1700
Data Index: 4086154 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.5918. Min Act: -0.1700
Data Index: 1745812 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.4981. Min Act: -0.1700
Data Index: 7632624 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.4356. Min Act: -0.1700
Data Index: 114809 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.4043. Min Act: -0.1700
Data Index: 2347155 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.3418. Min Act: -0.1700
Data Index: 1234311 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.3106. Min Act: -0.1700
Data Index: 6456857 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2793. Min Act: -0.1700
Data Index: 153557 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2481. Min Act: -0.1700
Data Index: 1544 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2481. Min Act: -0.1700
Data Index: 8396376 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2481. Min Act: -0.1700
Data Index: 586540 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2481. Min Act: -0.1700
Data Index: 15838 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2481. Min Act: -0.1700
Data Index: 7915627 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2481. Min Act: -0.1700
Data Index: 6904963 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2168. Min Act: -0.1700
Data Index: 2203019 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2168. Min Act: -0.1700
Data Index: 7079928 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.2168. Min Act: -0.1700
Data Index: 5526879 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.1856. Min Act: -0.1700
Data Index: 1191806 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.1856. Min Act: -0.1700
Data Index: 2490478 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9043. Min Range: -5.9043
Max Act: 5.1856. Min Act: -0.1700
Data Index: 7639613 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19