Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5253 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.7128. Min Act: -0.1700
Data Index: 2218129 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.6190. Min Act: -0.1700
Data Index: 598652 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.4628. Min Act: -0.1700
Data Index: 1171634 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.4003. Min Act: -0.1700
Data Index: 5771477 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.3690. Min Act: -0.1700
Data Index: 1902600 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.4003. Min Act: -0.1700
Data Index: 6035600 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.3690. Min Act: -0.1700
Data Index: 3674906 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.3378. Min Act: -0.1700
Data Index: 1702556 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2753. Min Act: -0.1700
Data Index: 3439504 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.3065. Min Act: -0.1700
Data Index: 888022 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2753. Min Act: -0.1700
Data Index: 6281327 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.3065. Min Act: -0.1700
Data Index: 4781593 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2753. Min Act: -0.1700
Data Index: 8626758 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2753. Min Act: -0.1700
Data Index: 7484931 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2753. Min Act: -0.1700
Data Index: 6127011 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2440. Min Act: -0.1700
Data Index: 6294918 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2128. Min Act: -0.1700
Data Index: 2241511 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.2128. Min Act: -0.1700
Data Index: 5176088 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.1815. Min Act: -0.1700
Data Index: 109077 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7128. Min Range: -7.7128
Max Act: 7.1815. Min Act: -0.1700
Data Index: 6380575 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19