Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.5918. Min Act: -0.1700
Data Index: 3782566 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.5293. Min Act: -0.1700
Data Index: 2099966 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.5293. Min Act: -0.1700
Data Index: 3782563 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.4355. Min Act: -0.1700
Data Index: 3782560 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.4668. Min Act: -0.1700
Data Index: 3782561 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.4355. Min Act: -0.1700
Data Index: 2099965 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.4355. Min Act: -0.1700
Data Index: 2099969 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.4355. Min Act: -0.1700
Data Index: 2099964 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.4043. Min Act: -0.1700
Data Index: 2099967 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.3730. Min Act: -0.1700
Data Index: 2099968 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.3105. Min Act: -0.1700
Data Index: 3782565 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.3730. Min Act: -0.1700
Data Index: 2099970 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.3105. Min Act: -0.1700
Data Index: 4156558 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2793. Min Act: -0.1700
Data Index: 1636346 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2793. Min Act: -0.1700
Data Index: 1636359 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2793. Min Act: -0.1700
Data Index: 3782559 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2480. Min Act: -0.1700
Data Index: 4545995 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2168. Min Act: -0.1700
Data Index: 6043560 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2793. Min Act: -0.1700
Data Index: 6894049 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5918. Min Range: -6.5918
Max Act: 6.2480. Min Act: -0.1700
Data Index: 1593817 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19