Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.9372. Min Act: -0.1700
Data Index: 5532150 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.7809. Min Act: -0.1700
Data Index: 8022745 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.7184. Min Act: -0.1700
Data Index: 2789104 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.7184. Min Act: -0.1700
Data Index: 1149037 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1699
Data Index: 7971284 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 940218 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 5717608 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 3628849 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 7277093 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6559. Min Act: -0.1700
Data Index: 8667438 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 6668431 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6247. Min Act: -0.1700
Data Index: 6215163 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6559. Min Act: -0.1700
Data Index: 3967898 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 8237229 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6872. Min Act: -0.1700
Data Index: 1803764 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6247. Min Act: -0.1700
Data Index: 7960415 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6247. Min Act: -0.1700
Data Index: 2795147 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.5934. Min Act: -0.1700
Data Index: 462606 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.5934. Min Act: -0.1700
Data Index: 6685706 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9372. Min Range: -5.9372
Max Act: 5.6247. Min Act: -0.1700
Data Index: 4259537 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19