Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0380. Min Range: -7.0380
Max Act: 7.0380. Min Act: -0.1700
Data Index: 6017463 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.7567. Min Act: -0.1700
Data Index: 6652165 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.6630. Min Act: -0.1700
Data Index: 6037 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.5692. Min Act: -0.1700
Data Index: 8390503 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.5067. Min Act: -0.1700
Data Index: 7873923 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.4755. Min Act: -0.1700
Data Index: 2898164 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.4130. Min Act: -0.1700
Data Index: 7207273 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.4442. Min Act: -0.1700
Data Index: 8078437 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.3505. Min Act: -0.1700
Data Index: 2729736 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.3505. Min Act: -0.1700
Data Index: 4763932 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.3505. Min Act: -0.1700
Data Index: 7965438 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2880. Min Act: -0.1700
Data Index: 4705513 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2880. Min Act: -0.1700
Data Index: 91444 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.3192. Min Act: -0.1700
Data Index: 3586795 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2880. Min Act: -0.1700
Data Index: 5974995 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2880. Min Act: -0.1700
Data Index: 4266777 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2255. Min Act: -0.1700
Data Index: 3970479 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2255. Min Act: -0.1700
Data Index: 1794915 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2255. Min Act: -0.1700
Data Index: 3022102 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0380. Min Range: -7.0380
Max Act: 6.2255. Min Act: -0.1700
Data Index: 6072947 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19