Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1056. Min Range: -7.1056
Max Act: 7.1056. Min Act: -0.1700
Data Index: 3081072 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.9806. Min Act: -0.1700
Data Index: 5508110 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1056. Min Range: -7.1056
Max Act: 7.0431. Min Act: -0.1700
Data Index: 853029 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1056. Min Range: -7.1056
Max Act: 7.0119. Min Act: -0.1700
Data Index: 1203368 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.9494. Min Act: -0.1700
Data Index: 4299002 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.8869. Min Act: -0.1700
Data Index: 7641741 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.8556. Min Act: -0.1700
Data Index: 350492 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.7931. Min Act: -0.1700
Data Index: 434746 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.8556. Min Act: -0.1700
Data Index: 5011341 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.8244. Min Act: -0.1700
Data Index: 730420 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.7931. Min Act: -0.1700
Data Index: 3629923 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.7619. Min Act: -0.1700
Data Index: 4189985 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.7306. Min Act: -0.1700
Data Index: 2006307 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6994. Min Act: -0.1700
Data Index: 4159252 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6994. Min Act: -0.1700
Data Index: 730417 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6994. Min Act: -0.1700
Data Index: 640389 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6994. Min Act: -0.1700
Data Index: 6683037 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6681. Min Act: -0.1700
Data Index: 1873255 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6681. Min Act: -0.1700
Data Index: 7555925 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1056. Min Range: -7.1056
Max Act: 6.6056. Min Act: -0.1700
Data Index: 2427910 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19