Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.2693. Min Act: -0.1700
Data Index: 8062206 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2693. Min Range: -5.2693
Max Act: 5.0818. Min Act: -0.1700
Data Index: 974007 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.9881. Min Act: -0.1700
Data Index: 7389147 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.8631. Min Act: -0.1700
Data Index: 444360 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.8631. Min Act: -0.1700
Data Index: 8507366 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.8318. Min Act: -0.1700
Data Index: 864587 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.8318. Min Act: -0.1700
Data Index: 8295730 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.8006. Min Act: -0.1700
Data Index: 1656705 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.8006. Min Act: -0.1700
Data Index: 7950808 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7693. Min Act: -0.1700
Data Index: 3117668 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7693. Min Act: -0.1700
Data Index: 880463 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7693. Min Act: -0.1700
Data Index: 4884825 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7693. Min Act: -0.1700
Data Index: 275865 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 3442744 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 8570093 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2382211 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 506003 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2575681 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7381. Min Act: -0.1700
Data Index: 169305 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2693. Min Range: -5.2693
Max Act: 4.7068. Min Act: -0.1700
Data Index: 4109982 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19