Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.5873. Min Act: -0.1700
Data Index: 2331976 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.4623. Min Act: -0.1700
Data Index: 2331975 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.3998. Min Act: -0.1700
Data Index: 2713 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.3373. Min Act: -0.1700
Data Index: 8441181 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.2748. Min Act: -0.1700
Data Index: 8137124 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.2748. Min Act: -0.1700
Data Index: 7845652 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.2748. Min Act: -0.1700
Data Index: 7124536 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.2123. Min Act: -0.1700
Data Index: 6317086 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.2123. Min Act: -0.1700
Data Index: 2754576 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.2123. Min Act: -0.1700
Data Index: 8283229 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.1498. Min Act: -0.1700
Data Index: 1860326 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0873. Min Act: -0.1700
Data Index: 3686787 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.1498. Min Act: -0.1700
Data Index: 635791 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0248. Min Act: -0.1700
Data Index: 5340727 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0873. Min Act: -0.1700
Data Index: 404930 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.1498. Min Act: -0.1700
Data Index: 2712 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0873. Min Act: -0.1700
Data Index: 1860324 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0873. Min Act: -0.1700
Data Index: 1860325 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0248. Min Act: -0.1700
Data Index: 3452526 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5873. Min Range: -9.5873
Max Act: 9.0248. Min Act: -0.1700
Data Index: 8126819 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19