Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1064. Min Range: -4.1064
Max Act: 4.0751. Min Act: -0.1700
Data Index: 4331646 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1064. Min Range: -4.1064
Max Act: 4.1064. Min Act: -0.1700
Data Index: 2023533 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1064. Min Range: -4.1064
Max Act: 4.1064. Min Act: -0.1700
Data Index: 2814415 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1064. Min Range: -4.1064
Max Act: 4.0751. Min Act: -0.1700
Data Index: 6673055 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1064. Min Range: -4.1064
Max Act: 4.0438. Min Act: -0.1700
Data Index: 4864660 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9813. Min Act: -0.1700
Data Index: 2756964 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1064. Min Range: -4.1064
Max Act: 4.0126. Min Act: -0.1700
Data Index: 2988535 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9813. Min Act: -0.1700
Data Index: 5651454 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9813. Min Act: -0.1700
Data Index: 6725882 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9813. Min Act: -0.1700
Data Index: 704387 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9501. Min Act: -0.1700
Data Index: 2848537 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9501. Min Act: -0.1700
Data Index: 791098 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9501. Min Act: -0.1700
Data Index: 331950 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9501. Min Act: -0.1700
Data Index: 8097010 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9501. Min Act: -0.1700
Data Index: 3969624 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9501. Min Act: -0.1700
Data Index: 425146 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9188. Min Act: -0.1700
Data Index: 2606292 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9188. Min Act: -0.1700
Data Index: 4600788 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9188. Min Act: -0.1700
Data Index: 2421622 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1064. Min Range: -4.1064
Max Act: 3.9188. Min Act: -0.1700
Data Index: 3007137 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19