Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5072 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1678. Min Range: -6.1678
Max Act: 6.1678. Min Act: -0.1700
Data Index: 784877 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.8553. Min Act: -0.1700
Data Index: 1621466 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.8553. Min Act: -0.1700
Data Index: 3892416 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.8553. Min Act: -0.1700
Data Index: 8024194 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.7928. Min Act: -0.1700
Data Index: 7171297 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.7616. Min Act: -0.1700
Data Index: 4234188 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.7303. Min Act: -0.1700
Data Index: 5009571 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.7616. Min Act: -0.1700
Data Index: 5061064 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6991. Min Act: -0.1700
Data Index: 7737480 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6991. Min Act: -0.1700
Data Index: 2879915 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2393501 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7732777 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3751902 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 8368465 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 4587244 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 1886934 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 7227019 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6678. Min Act: -0.1700
Data Index: 8024190 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 2220026 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1678. Min Range: -6.1678
Max Act: 5.6366. Min Act: -0.1700
Data Index: 529537 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19