Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2242. Min Range: -7.2242
Max Act: 7.2242. Min Act: -0.1700
Data Index: 3498095 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2242. Min Range: -7.2242
Max Act: 7.1617. Min Act: -0.1700
Data Index: 7646665 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2242. Min Range: -7.2242
Max Act: 7.0992. Min Act: -0.1700
Data Index: 163241 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.9429. Min Act: -0.1700
Data Index: 5034643 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.9117. Min Act: -0.1700
Data Index: 2124292 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.9117. Min Act: -0.1700
Data Index: 6061258 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.9117. Min Act: -0.1700
Data Index: 3338528 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.8804. Min Act: -0.1700
Data Index: 6083573 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.8492. Min Act: -0.1700
Data Index: 8340820 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.8179. Min Act: -0.1700
Data Index: 5107321 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.8179. Min Act: -0.1700
Data Index: 4516717 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.8179. Min Act: -0.1700
Data Index: 4286838 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7867. Min Act: -0.1700
Data Index: 5787112 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7867. Min Act: -0.1700
Data Index: 7631294 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7867. Min Act: -0.1700
Data Index: 4904968 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7867. Min Act: -0.1700
Data Index: 1472829 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7554. Min Act: -0.1700
Data Index: 2003026 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7242. Min Act: -0.1700
Data Index: 6925227 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.6929. Min Act: -0.1700
Data Index: 98983 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2242. Min Range: -7.2242
Max Act: 6.7242. Min Act: -0.1700
Data Index: 294759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19