Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4559 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.8392. Min Act: -0.1700
Data Index: 1791844 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.7142. Min Act: -0.1700
Data Index: 3041837 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.6205. Min Act: -0.1700
Data Index: 4846321 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.6205. Min Act: -0.1700
Data Index: 3996608 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5892. Min Act: -0.1700
Data Index: 503032 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.6205. Min Act: -0.1700
Data Index: 276184 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5580. Min Act: -0.1700
Data Index: 3763619 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5580. Min Act: -0.1700
Data Index: 1999571 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5267. Min Act: -0.1700
Data Index: 5590486 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5892. Min Act: -0.1700
Data Index: 6788040 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5267. Min Act: -0.1700
Data Index: 7614119 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5267. Min Act: -0.1700
Data Index: 2175524 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5267. Min Act: -0.1700
Data Index: 8363667 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5580. Min Act: -0.1700
Data Index: 1635946 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5267. Min Act: -0.1700
Data Index: 1400999 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.5267. Min Act: -0.1700
Data Index: 143942 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.4955. Min Act: -0.1700
Data Index: 8363099 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.4955. Min Act: -0.1700
Data Index: 7478470 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.4955. Min Act: -0.1700
Data Index: 1764396 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8392. Min Range: -6.8392
Max Act: 6.4955. Min Act: -0.1700
Data Index: 4642847 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19