Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4405 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2113. Min Range: -6.2113
Max Act: 6.2113. Min Act: -0.1700
Data Index: 620737 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2113. Min Range: -6.2113
Max Act: 6.0863. Min Act: -0.1700
Data Index: 346847 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2113. Min Range: -6.2113
Max Act: 6.0551. Min Act: -0.1700
Data Index: 6214812 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2113. Min Range: -6.2113
Max Act: 6.0238. Min Act: -0.1700
Data Index: 28493 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2113. Min Range: -6.2113
Max Act: 6.0238. Min Act: -0.1700
Data Index: 1647371 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2113. Min Range: -6.2113
Max Act: 6.0238. Min Act: -0.1700
Data Index: 3108107 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.9926. Min Act: -0.1700
Data Index: 6643777 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.9301. Min Act: -0.1700
Data Index: 7034912 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.8988. Min Act: -0.1700
Data Index: 7197208 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.8988. Min Act: -0.1700
Data Index: 8728781 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.8051. Min Act: -0.1700
Data Index: 944145 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7738. Min Act: -0.1700
Data Index: 7109458 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7738. Min Act: -0.1700
Data Index: 8632487 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7738. Min Act: -0.1700
Data Index: 3246816 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.8051. Min Act: -0.1700
Data Index: 6255616 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7738. Min Act: -0.1700
Data Index: 2105667 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7426. Min Act: -0.1700
Data Index: 2006725 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7426. Min Act: -0.1700
Data Index: 4602424 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7426. Min Act: -0.1700
Data Index: 5499411 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2113. Min Range: -6.2113
Max Act: 5.7113. Min Act: -0.1700
Data Index: 6788596 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19