Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1888 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.7840. Min Act: -0.1700
Data Index: 2922059 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.7215. Min Act: -0.1700
Data Index: 5997761 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.6903. Min Act: -0.1700
Data Index: 2530064 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.6903. Min Act: -0.1700
Data Index: 4764643 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.6590. Min Act: -0.1700
Data Index: 7456099 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5965. Min Act: -0.1700
Data Index: 1703830 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5965. Min Act: -0.1700
Data Index: 2362390 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5653. Min Act: -0.1700
Data Index: 7456071 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5653. Min Act: -0.1700
Data Index: 1971505 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 8806560 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 2225358 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 5629028 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5028. Min Act: -0.1700
Data Index: 4000792 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 5702640 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 6634179 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 4987588 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5340. Min Act: -0.1700
Data Index: 6942310 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5028. Min Act: -0.1700
Data Index: 78201 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.5028. Min Act: -0.1700
Data Index: 4688540 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7840. Min Range: -4.7840
Max Act: 4.4403. Min Act: -0.1700
Data Index: 1256209 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19