Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6515. Min Range: -8.6515
Max Act: 8.6515. Min Act: -0.1700
Data Index: 2822519 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6515. Min Range: -8.6515
Max Act: 8.0265. Min Act: -0.1700
Data Index: 8571399 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.9640. Min Act: -0.1700
Data Index: 6941345 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.8702. Min Act: -0.1700
Data Index: 4875445 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.8390. Min Act: -0.1700
Data Index: 2526201 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.8390. Min Act: -0.1700
Data Index: 6328541 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.8077. Min Act: -0.1700
Data Index: 2340907 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7765. Min Act: -0.1700
Data Index: 4310699 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7765. Min Act: -0.1700
Data Index: 7672613 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7452. Min Act: -0.1700
Data Index: 1248062 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7452. Min Act: -0.1700
Data Index: 5454819 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7140. Min Act: -0.1700
Data Index: 6137052 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7452. Min Act: -0.1700
Data Index: 422550 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7452. Min Act: -0.1700
Data Index: 4937363 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.7140. Min Act: -0.1700
Data Index: 376402 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.6515. Min Act: -0.1700
Data Index: 5382195 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.6515. Min Act: -0.1700
Data Index: 3513516 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.6202. Min Act: -0.1700
Data Index: 6319714 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.6202. Min Act: -0.1700
Data Index: 7757234 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6515. Min Range: -8.6515
Max Act: 7.5890. Min Act: -0.1700
Data Index: 1190195 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19