Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3722. Min Range: -7.3722
Max Act: 7.3722. Min Act: -0.1700
Data Index: 1034232 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.9972. Min Act: -0.1700
Data Index: 1976030 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.8722. Min Act: -0.1700
Data Index: 656662 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.7784. Min Act: -0.1700
Data Index: 6278050 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.7784. Min Act: -0.1700
Data Index: 543527 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.7159. Min Act: -0.1700
Data Index: 8210043 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.6847. Min Act: -0.1700
Data Index: 6928655 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.6222. Min Act: -0.1700
Data Index: 4467111 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.6222. Min Act: -0.1700
Data Index: 1446573 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.6534. Min Act: -0.1700
Data Index: 5511575 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5909. Min Act: -0.1700
Data Index: 1293400 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5909. Min Act: -0.1700
Data Index: 8495188 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5597. Min Act: -0.1700
Data Index: 2381846 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5909. Min Act: -0.1700
Data Index: 7378390 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5597. Min Act: -0.1700
Data Index: 7644202 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5597. Min Act: -0.1700
Data Index: 5773974 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5284. Min Act: -0.1700
Data Index: 3482488 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5284. Min Act: -0.1700
Data Index: 5266870 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5284. Min Act: -0.1700
Data Index: 2963021 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3722. Min Range: -7.3722
Max Act: 6.5284. Min Act: -0.1700
Data Index: 592804 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19