Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.6076. Min Act: -0.1700
Data Index: 7980266 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.5139. Min Act: -0.1700
Data Index: 4619436 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.5139. Min Act: -0.1700
Data Index: 1632945 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.4514. Min Act: -0.1700
Data Index: 2157998 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.3264. Min Act: -0.1700
Data Index: 4592797 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.2326. Min Act: -0.1700
Data Index: 1257783 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.2014. Min Act: -0.1700
Data Index: 1515415 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1701. Min Act: -0.1700
Data Index: 4860137 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1701. Min Act: -0.1700
Data Index: 3175660 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1701. Min Act: -0.1700
Data Index: 7032769 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1389. Min Act: -0.1700
Data Index: 1729091 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1076. Min Act: -0.1700
Data Index: 4174877 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1076. Min Act: -0.1700
Data Index: 951268 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1076. Min Act: -0.1700
Data Index: 6192789 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1076. Min Act: -0.1700
Data Index: 667313 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.0764. Min Act: -0.1700
Data Index: 6251868 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.1076. Min Act: -0.1700
Data Index: 4642127 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.0764. Min Act: -0.1700
Data Index: 7154793 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.0451. Min Act: -0.1700
Data Index: 3775650 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6076. Min Range: -7.6076
Max Act: 7.0764. Min Act: -0.1700
Data Index: 2769380 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19