Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 98 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.8139. Min Act: -0.1700
Data Index: 7055399 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.7201. Min Act: -0.1700
Data Index: 8653148 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6576. Min Act: -0.1700
Data Index: 7546093 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.6264. Min Act: -0.1700
Data Index: 6071973 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.5951. Min Act: -0.1700
Data Index: 35865 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.5639. Min Act: -0.1700
Data Index: 450000 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.3451. Min Act: -0.1700
Data Index: 4180833 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.3451. Min Act: -0.1700
Data Index: 2296407 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 391144 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.3139. Min Act: -0.1700
Data Index: 975268 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.3139. Min Act: -0.1700
Data Index: 3560687 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 5124387 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 4936243 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 4080979 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 552490 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2826. Min Act: -0.1700
Data Index: 4938310 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2514. Min Act: -0.1700
Data Index: 5156874 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2514. Min Act: -0.1700
Data Index: 3970603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2201. Min Act: -0.1700
Data Index: 8394966 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8139. Min Range: -4.8139
Max Act: 4.2201. Min Act: -0.1700
Data Index: 7474717 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19