Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3184 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5442. Min Range: -6.5442
Max Act: 6.5442. Min Act: -0.1700
Data Index: 4480068 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5442. Min Range: -6.5442
Max Act: 6.1692. Min Act: -0.1700
Data Index: 4433159 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5442. Min Range: -6.5442
Max Act: 6.1379. Min Act: -0.1700
Data Index: 227236 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5442. Min Range: -6.5442
Max Act: 6.0754. Min Act: -0.1700
Data Index: 7413878 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5442. Min Range: -6.5442
Max Act: 6.1067. Min Act: -0.1700
Data Index: 5906645 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.9504. Min Act: -0.1700
Data Index: 1173919 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.8879. Min Act: -0.1700
Data Index: 2437608 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.8879. Min Act: -0.1700
Data Index: 2692572 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.5754. Min Act: -0.1700
Data Index: 5718265 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.5129. Min Act: -0.1700
Data Index: 2420118 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.5129. Min Act: -0.1700
Data Index: 3614626 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.4817. Min Act: -0.1700
Data Index: 7774313 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.4504. Min Act: -0.1700
Data Index: 7558498 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.4504. Min Act: -0.1700
Data Index: 8726412 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.4817. Min Act: -0.1700
Data Index: 4993820 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.4192. Min Act: -0.1700
Data Index: 7322625 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3229318 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.3567. Min Act: -0.1700
Data Index: 1390811 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.4192. Min Act: -0.1700
Data Index: 5041921 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5442. Min Range: -6.5442
Max Act: 5.3879. Min Act: -0.1700
Data Index: 7652068 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19