Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4573 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.8733. Min Act: -0.1700
Data Index: 1192383 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.8108. Min Act: -0.1700
Data Index: 6563062 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.4983. Min Act: -0.1700
Data Index: 156424 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.4983. Min Act: -0.1700
Data Index: 4371850 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.4358. Min Act: -0.1700
Data Index: 2564911 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.4983. Min Act: -0.1700
Data Index: 5498287 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.4358. Min Act: -0.1700
Data Index: 708173 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.4358. Min Act: -0.1700
Data Index: 922740 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.3733. Min Act: -0.1700
Data Index: 4804517 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.3733. Min Act: -0.1700
Data Index: 5082467 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.3108. Min Act: -0.1700
Data Index: 5877023 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.3733. Min Act: -0.1700
Data Index: 3352769 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.3108. Min Act: -0.1700
Data Index: 1668162 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.3108. Min Act: -0.1700
Data Index: 8679726 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.2796. Min Act: -0.1700
Data Index: 8798197 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.2483. Min Act: -0.1700
Data Index: 2516738 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.1858. Min Act: -0.1700
Data Index: 2953826 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.2171. Min Act: -0.1700
Data Index: 4618223 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.1858. Min Act: -0.1700
Data Index: 2063971 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8733. Min Range: -7.8733
Max Act: 7.2171. Min Act: -0.1700
Data Index: 2516739 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19