Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1407 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.2989. Min Act: -0.1700
Data Index: 1320848 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.2051. Min Act: -0.1700
Data Index: 8257451 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.1739. Min Act: -0.1700
Data Index: 7040672 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.1114. Min Act: -0.1700
Data Index: 6031112 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.0801. Min Act: -0.1700
Data Index: 8261765 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.0801. Min Act: -0.1700
Data Index: 6926021 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.0489. Min Act: -0.1700
Data Index: 2549267 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.0489. Min Act: -0.1700
Data Index: 8107831 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2989. Min Range: -4.2989
Max Act: 4.0176. Min Act: -0.1700
Data Index: 8106372 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9863. Min Act: -0.1700
Data Index: 5055753 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9863. Min Act: -0.1700
Data Index: 2373591 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 7604526 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 332240 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 4030038 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 3335773 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 3118399 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 5030483 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 74908 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9238. Min Act: -0.1700
Data Index: 7759669 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2989. Min Range: -4.2989
Max Act: 3.9551. Min Act: -0.1700
Data Index: 5388719 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19