Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4878 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.2332. Min Act: -0.1700
Data Index: 6827977 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.2019. Min Act: -0.1699
Data Index: 5225214 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.1081. Min Act: -0.1700
Data Index: 398064 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.0769. Min Act: -0.1700
Data Index: 3126443 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.0769. Min Act: -0.1700
Data Index: 1818936 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.0456. Min Act: -0.1700
Data Index: 8276945 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2332. Min Range: -4.2332
Max Act: 4.0144. Min Act: -0.1700
Data Index: 4213033 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9831. Min Act: -0.1700
Data Index: 6299132 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9831. Min Act: -0.1700
Data Index: 2797759 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9518. Min Act: -0.1700
Data Index: 6643311 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9518. Min Act: -0.1700
Data Index: 1717076 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9518. Min Act: -0.1700
Data Index: 7180767 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9518. Min Act: -0.1700
Data Index: 403666 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9518. Min Act: -0.1700
Data Index: 8084547 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9518. Min Act: -0.1700
Data Index: 1086681 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9206. Min Act: -0.1700
Data Index: 2144722 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9206. Min Act: -0.1700
Data Index: 2571210 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9206. Min Act: -0.1700
Data Index: 4474712 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9206. Min Act: -0.1700
Data Index: 6514447 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2332. Min Range: -4.2332
Max Act: 3.9206. Min Act: -0.1700
Data Index: 7719036 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19