Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0991. Min Range: -6.0991
Max Act: 6.0991. Min Act: -0.1700
Data Index: 4088546 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0991. Min Range: -6.0991
Max Act: 6.0366. Min Act: -0.1700
Data Index: 4301684 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.9741. Min Act: -0.1700
Data Index: 7842402 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.9741. Min Act: -0.1700
Data Index: 760752 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.9116. Min Act: -0.1700
Data Index: 4672134 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.8803. Min Act: -0.1700
Data Index: 2829560 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.8491. Min Act: -0.1700
Data Index: 4270116 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.7553. Min Act: -0.1700
Data Index: 8053129 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6928. Min Act: -0.1700
Data Index: 2092883 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6616. Min Act: -0.1700
Data Index: 7642598 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6616. Min Act: -0.1700
Data Index: 4382108 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6928. Min Act: -0.1700
Data Index: 2764682 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6303. Min Act: -0.1700
Data Index: 6672707 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6303. Min Act: -0.1700
Data Index: 7234007 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.5991. Min Act: -0.1700
Data Index: 2489021 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6303. Min Act: -0.1700
Data Index: 4983612 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6616. Min Act: -0.1700
Data Index: 892161 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.6303. Min Act: -0.1700
Data Index: 5267773 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.5678. Min Act: -0.1700
Data Index: 4258829 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0991. Min Range: -6.0991
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5002218 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19