Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1810 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.5932. Min Act: -0.1700
Data Index: 1746776 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.5932. Min Act: -0.1700
Data Index: 4959317 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.5932. Min Act: -0.1700
Data Index: 4777930 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.5307. Min Act: -0.1700
Data Index: 8630724 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.5307. Min Act: -0.1700
Data Index: 672629 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.5307. Min Act: -0.1697
Data Index: 5496316 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4682. Min Act: -0.1700
Data Index: 5740985 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4682. Min Act: -0.1700
Data Index: 1042035 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4682. Min Act: -0.1700
Data Index: 6279557 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4057. Min Act: -0.1700
Data Index: 1877648 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4057. Min Act: -0.1700
Data Index: 5195452 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4057. Min Act: -0.1700
Data Index: 3012583 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 6470126 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 6237725 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 4815028 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 1897257 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 552690 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 552694 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.4057. Min Act: -0.1700
Data Index: 6632488 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5932. Min Range: -7.5932
Max Act: 7.3432. Min Act: -0.1700
Data Index: 7623565 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19