Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1930. Min Range: -7.1930
Max Act: 7.1930. Min Act: -0.1700
Data Index: 3486779 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.4742. Min Act: -0.1700
Data Index: 5468900 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.2242. Min Act: -0.1700
Data Index: 1671758 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.1930. Min Act: -0.1700
Data Index: 2303034 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.1930. Min Act: -0.1700
Data Index: 1946684 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.1930. Min Act: -0.1700
Data Index: 2319607 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3667749 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.1305. Min Act: -0.1700
Data Index: 2490804 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.1305. Min Act: -0.1700
Data Index: 350587 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0992. Min Act: -0.1700
Data Index: 3375935 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0992. Min Act: -0.1700
Data Index: 6734787 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0367. Min Act: -0.1700
Data Index: 2135753 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0367. Min Act: -0.1700
Data Index: 3248624 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0367. Min Act: -0.1700
Data Index: 6478611 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0055. Min Act: -0.1700
Data Index: 2040503 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0055. Min Act: -0.1700
Data Index: 7475835 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1930. Min Range: -7.1930
Max Act: 6.0055. Min Act: -0.1700
Data Index: 3753088 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1930. Min Range: -7.1930
Max Act: 5.9742. Min Act: -0.1700
Data Index: 3701382 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1930. Min Range: -7.1930
Max Act: 5.9742. Min Act: -0.1700
Data Index: 5167341 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1930. Min Range: -7.1930
Max Act: 5.9430. Min Act: -0.1700
Data Index: 1277668 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19