Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.9746. Min Act: -0.1700
Data Index: 8674643 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.9746. Min Act: -0.1700
Data Index: 32966 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.9746. Min Act: -0.1700
Data Index: 235489 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.9121. Min Act: -0.1700
Data Index: 7225040 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.8496. Min Act: -0.1700
Data Index: 7345265 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.8183. Min Act: -0.1700
Data Index: 4544935 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.8183. Min Act: -0.1700
Data Index: 1777598 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.8183. Min Act: -0.1700
Data Index: 2626033 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.8496. Min Act: -0.1700
Data Index: 3032577 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7871. Min Act: -0.1700
Data Index: 2731641 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3195361 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7558. Min Act: -0.1700
Data Index: 8290243 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7871. Min Act: -0.1700
Data Index: 6101360 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7871. Min Act: -0.1700
Data Index: 42117 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7558. Min Act: -0.1700
Data Index: 648460 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7871. Min Act: -0.1700
Data Index: 7886018 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7558. Min Act: -0.1700
Data Index: 3055644 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7558. Min Act: -0.1700
Data Index: 1352920 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7558. Min Act: -0.1700
Data Index: 4675746 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9746. Min Range: -5.9746
Max Act: 5.7558. Min Act: -0.1700
Data Index: 6611042 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19