Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4205 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.9003. Min Act: -0.1700
Data Index: 486813 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.6503. Min Act: -0.1700
Data Index: 3165268 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.5253. Min Act: -0.1700
Data Index: 7262551 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4941. Min Act: -0.1700
Data Index: 5097973 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4941. Min Act: -0.1700
Data Index: 735415 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4628. Min Act: -0.1700
Data Index: 421011 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4316. Min Act: -0.1700
Data Index: 5926751 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4316. Min Act: -0.1700
Data Index: 550434 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4003. Min Act: -0.1700
Data Index: 2319514 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.4003. Min Act: -0.1700
Data Index: 4772070 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.3691. Min Act: -0.1700
Data Index: 4744404 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.3066. Min Act: -0.1700
Data Index: 7927924 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.3066. Min Act: -0.1700
Data Index: 2229791 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.2753. Min Act: -0.1700
Data Index: 582486 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.3066. Min Act: -0.1700
Data Index: 6348594 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.2128. Min Act: -0.1700
Data Index: 274944 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.2128. Min Act: -0.1700
Data Index: 4787084 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.1816. Min Act: -0.1700
Data Index: 373562 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.1816. Min Act: -0.1700
Data Index: 704999 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9003. Min Range: -7.9003
Max Act: 7.1503. Min Act: -0.1700
Data Index: 7594481 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19