Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 694 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.9480. Min Act: -0.1700
Data Index: 4519856 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.8855. Min Act: -0.1700
Data Index: 2215980 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.8543. Min Act: -0.1700
Data Index: 2429844 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.7605. Min Act: -0.1700
Data Index: 2345422 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.7293. Min Act: -0.1700
Data Index: 8737275 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.6980. Min Act: -0.1700
Data Index: 8191088 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.6980. Min Act: -0.1700
Data Index: 5033040 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.6980. Min Act: -0.1700
Data Index: 128030 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.6980. Min Act: -0.1700
Data Index: 1500715 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.6355. Min Act: -0.1700
Data Index: 4415855 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 3871159 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 4303821 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 5074911 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 2356162 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5730. Min Act: -0.1700
Data Index: 1132879 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5418. Min Act: -0.1700
Data Index: 299636 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5105. Min Act: -0.1700
Data Index: 5716963 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.5105. Min Act: -0.1700
Data Index: 2346737 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4300013 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9480. Min Range: -7.9480
Max Act: 7.4793. Min Act: -0.1700
Data Index: 7704792 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19