Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.6475. Min Act: -0.1700
Data Index: 4047113 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.6475. Min Act: -0.1700
Data Index: 7834078 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.3350. Min Act: -0.1700
Data Index: 8787375 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.3350. Min Act: -0.1700
Data Index: 8688081 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.3350. Min Act: -0.1700
Data Index: 530880 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.3350. Min Act: -0.1700
Data Index: 2246985 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2725. Min Act: -0.1700
Data Index: 6106565 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2725. Min Act: -0.1700
Data Index: 7026666 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2725. Min Act: -0.1700
Data Index: 5891153 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2100. Min Act: -0.1700
Data Index: 8451216 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2100. Min Act: -0.1700
Data Index: 2847434 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2100. Min Act: -0.1700
Data Index: 208619 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.2100. Min Act: -0.1700
Data Index: 297337 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 2738145 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 5842444 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 7336395 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 3199256 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 1291401 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 1539962 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6475. Min Range: -8.6475
Max Act: 8.1475. Min Act: -0.1700
Data Index: 5258530 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19