Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.4100. Min Act: -0.1700
Data Index: 5005014 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.4100. Min Act: -0.1700
Data Index: 5929704 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3475. Min Act: -0.1700
Data Index: 7967734 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2850. Min Act: -0.1700
Data Index: 2116013 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 5755610 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 7650540 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 3897056 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 2445470 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 6518206 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2225. Min Act: -0.1700
Data Index: 6104647 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 63143 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 782851 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2225. Min Act: -0.1700
Data Index: 7215711 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 5002410 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 194199 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 1774322 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1600. Min Act: -0.1700
Data Index: 7041330 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1600. Min Act: -0.1700
Data Index: 691393 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1600. Min Act: -0.1700
Data Index: 1835425 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1600. Min Act: -0.1700
Data Index: 7246627 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19