Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1757 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3315. Min Range: -6.3315
Max Act: 6.3315. Min Act: -0.1700
Data Index: 6283561 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3315. Min Range: -6.3315
Max Act: 6.2690. Min Act: -0.1700
Data Index: 6623748 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3315. Min Range: -6.3315
Max Act: 6.0815. Min Act: -0.1700
Data Index: 1396622 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3315. Min Range: -6.3315
Max Act: 6.0502. Min Act: -0.1700
Data Index: 4372761 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8940. Min Act: -0.1700
Data Index: 5107120 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8315. Min Act: -0.1700
Data Index: 6630906 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8627. Min Act: -0.1700
Data Index: 569621 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8002. Min Act: -0.1700
Data Index: 1414500 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8315. Min Act: -0.1700
Data Index: 4578703 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8315. Min Act: -0.1700
Data Index: 7626252 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8315. Min Act: -0.1700
Data Index: 8318539 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8002. Min Act: -0.1700
Data Index: 3675227 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8002. Min Act: -0.1700
Data Index: 8050168 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.8002. Min Act: -0.1700
Data Index: 8118038 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 243301 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 2428709 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 6442054 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 4347797 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 3390963 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3315. Min Range: -6.3315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 6947153 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19