Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.5524. Min Act: -0.1700
Data Index: 675629 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.5367. Min Act: -0.1700
Data Index: 3454189 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.4427. Min Act: -0.1700
Data Index: 6211509 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.4584. Min Act: -0.1700
Data Index: 4359239 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3800. Min Act: -0.1700
Data Index: 501514 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3800. Min Act: -0.1700
Data Index: 7261947 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3330. Min Act: -0.1700
Data Index: 7295682 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3643. Min Act: -0.1700
Data Index: 6526449 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3486. Min Act: -0.1700
Data Index: 3012076 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3486. Min Act: -0.1700
Data Index: 7328089 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3330. Min Act: -0.1700
Data Index: 533130 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3173. Min Act: -0.1700
Data Index: 3745449 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3486. Min Act: -0.1700
Data Index: 4986016 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3173. Min Act: -0.1700
Data Index: 4521541 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.2859. Min Act: -0.1700
Data Index: 557424 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.2859. Min Act: -0.1700
Data Index: 3527196 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.2859. Min Act: -0.1700
Data Index: 2908747 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3016. Min Act: -0.1700
Data Index: 4505434 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.3173. Min Act: -0.1700
Data Index: 5761002 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5524. Min Range: -3.5524
Max Act: 3.2859. Min Act: -0.1700
Data Index: 2627403 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19