Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4877. Min Act: -0.1700
Data Index: 2073936 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4877. Min Act: -0.1700
Data Index: 8358041 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4564. Min Act: -0.1700
Data Index: 8508825 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4564. Min Act: -0.1700
Data Index: 3136046 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4564. Min Act: -0.1700
Data Index: 3546139 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4564. Min Act: -0.1700
Data Index: 8350004 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4564. Min Act: -0.1700
Data Index: 7979097 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4564. Min Act: -0.1700
Data Index: 3736307 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.4252. Min Act: -0.1700
Data Index: 576097 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3939. Min Act: -0.1700
Data Index: 1441119 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3626. Min Act: -0.1700
Data Index: 7562438 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3626. Min Act: -0.1700
Data Index: 4005857 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3626. Min Act: -0.1700
Data Index: 469998 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3314. Min Act: -0.1700
Data Index: 6091774 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3314. Min Act: -0.1700
Data Index: 158935 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3314. Min Act: -0.1700
Data Index: 6588387 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3314. Min Act: -0.1700
Data Index: 5562362 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3314. Min Act: -0.1700
Data Index: 4141142 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3314. Min Act: -0.1700
Data Index: 2092852 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4877. Min Range: -4.4877
Max Act: 4.3001. Min Act: -0.1700
Data Index: 333595 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19