Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4643 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.7500. Min Act: -0.1700
Data Index: 976719 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.7020. Min Act: -0.1700
Data Index: 2244880 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6860. Min Act: -0.1700
Data Index: 7526513 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.7020. Min Act: -0.1700
Data Index: 2472921 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6860. Min Act: -0.1700
Data Index: 5368529 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6860. Min Act: -0.1700
Data Index: 7490595 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6700. Min Act: -0.1700
Data Index: 458231 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6700. Min Act: -0.1700
Data Index: 7696587 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6860. Min Act: -0.1700
Data Index: 5560068 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6379. Min Act: -0.1700
Data Index: 3303971 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6379. Min Act: -0.1700
Data Index: 4585116 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6379. Min Act: -0.1700
Data Index: 3023696 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6379. Min Act: -0.1700
Data Index: 7070407 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6379. Min Act: -0.1700
Data Index: 955180 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6218. Min Act: -0.1700
Data Index: 1720535 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6058. Min Act: -0.1700
Data Index: 29779 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6218. Min Act: -0.1700
Data Index: 1660090 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6218. Min Act: -0.1700
Data Index: 4440879 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6058. Min Act: -0.1700
Data Index: 3499803 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7500. Min Range: -2.7500
Max Act: 2.6058. Min Act: -0.1700
Data Index: 4834575 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19