Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.7156. Min Act: -0.1700
Data Index: 3638941 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5286570 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.6843. Min Act: -0.1700
Data Index: 8557259 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.6531. Min Act: -0.1700
Data Index: 1549843 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.6218. Min Act: -0.1700
Data Index: 6381402 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5593. Min Act: -0.1700
Data Index: 5761114 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5593. Min Act: -0.1700
Data Index: 3015480 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5281. Min Act: -0.1700
Data Index: 1829517 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4968. Min Act: -0.1700
Data Index: 8468399 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4968. Min Act: -0.1700
Data Index: 4159114 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4968. Min Act: -0.1700
Data Index: 3436336 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4968. Min Act: -0.1700
Data Index: 3347505 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 4467467 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 1661569 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4343. Min Act: -0.1700
Data Index: 2402064 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4031. Min Act: -0.1700
Data Index: 591229 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4031. Min Act: -0.1700
Data Index: 4271961 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.3718. Min Act: -0.1700
Data Index: 5101478 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.3718. Min Act: -0.1700
Data Index: 2409305 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.3718. Min Act: -0.1700
Data Index: 4016908 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19