Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.5997. Min Act: -0.1700
Data Index: 2878933 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 6047879 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3809. Min Act: -0.1700
Data Index: 5987545 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3184. Min Act: -0.1700
Data Index: 4588841 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7733992 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2559. Min Act: -0.1700
Data Index: 7352686 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2872. Min Act: -0.1700
Data Index: 6005344 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2872. Min Act: -0.1700
Data Index: 4853993 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2559. Min Act: -0.1700
Data Index: 3857505 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2559. Min Act: -0.1700
Data Index: 8138959 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2559. Min Act: -0.1700
Data Index: 5189881 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2559. Min Act: -0.1700
Data Index: 3394986 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2247. Min Act: -0.1700
Data Index: 4600717 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2247. Min Act: -0.1700
Data Index: 4837942 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2247. Min Act: -0.1700
Data Index: 4254143 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2247. Min Act: -0.1700
Data Index: 1474716 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2247. Min Act: -0.1700
Data Index: 2526297 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2559. Min Act: -0.1700
Data Index: 4565615 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.1934. Min Act: -0.1700
Data Index: 4904088 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.2247. Min Act: -0.1700
Data Index: 1885857 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19