Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4725 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.4696. Min Act: -0.1700
Data Index: 3318577 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.0946. Min Act: -0.1700
Data Index: 6235877 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.0008. Min Act: -0.1700
Data Index: 3987448 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.9696. Min Act: -0.1700
Data Index: 7051555 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.8446. Min Act: -0.1700
Data Index: 2127586 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.8446. Min Act: -0.1700
Data Index: 1971773 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.8133. Min Act: -0.1700
Data Index: 141332 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7821. Min Act: -0.1700
Data Index: 8702913 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7821. Min Act: -0.1700
Data Index: 6235439 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7508. Min Act: -0.1700
Data Index: 3271971 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 4137142 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 2593903 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 6574505 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 7345439 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 4425923 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 2050941 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.6883. Min Act: -0.1700
Data Index: 4685874 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.6883. Min Act: -0.1700
Data Index: 7620808 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.6883. Min Act: -0.1700
Data Index: 2792863 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.6571. Min Act: -0.1700
Data Index: 6944671 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19