Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 538 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1387. Min Range: -3.1387
Max Act: 3.1387. Min Act: -0.1700
Data Index: 1469619 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1387. Min Range: -3.1387
Max Act: 3.0757. Min Act: -0.1700
Data Index: 3573666 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.9967. Min Act: -0.1700
Data Index: 2518319 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.9651. Min Act: -0.1700
Data Index: 2150621 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.9493. Min Act: -0.1700
Data Index: 7796950 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.9176. Min Act: -0.1700
Data Index: 6134177 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8859. Min Act: -0.1700
Data Index: 470321 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8859. Min Act: -0.1700
Data Index: 1066771 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8859. Min Act: -0.1700
Data Index: 3446564 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8700. Min Act: -0.1700
Data Index: 8604417 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8541. Min Act: -0.1700
Data Index: 52114 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8700. Min Act: -0.1700
Data Index: 2616479 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8541. Min Act: -0.1700
Data Index: 175144 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8223. Min Act: -0.1700
Data Index: 3869805 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8223. Min Act: -0.1700
Data Index: 7874358 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8064. Min Act: -0.1700
Data Index: 436941 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.7905. Min Act: -0.1700
Data Index: 4059276 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8064. Min Act: -0.1700
Data Index: 6155526 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8064. Min Act: -0.1700
Data Index: 5523802 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1387. Min Range: -3.1387
Max Act: 2.8064. Min Act: -0.1700
Data Index: 8330119 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19