Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3683 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.9089. Min Act: -0.1700
Data Index: 6928808 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.8464. Min Act: -0.1700
Data Index: 5348267 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.7214. Min Act: -0.1700
Data Index: 8765080 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.7214. Min Act: -0.1700
Data Index: 6237102 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.7214. Min Act: -0.1700
Data Index: 5441645 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.6589. Min Act: -0.1700
Data Index: 3173473 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.5964. Min Act: -0.1700
Data Index: 76985 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.5964. Min Act: -0.1700
Data Index: 4685991 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.5339. Min Act: -0.1700
Data Index: 1020422 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.5964. Min Act: -0.1700
Data Index: 224376 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4714. Min Act: -0.1700
Data Index: 5543783 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4714. Min Act: -0.1700
Data Index: 8206941 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4714. Min Act: -0.1700
Data Index: 7840599 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4089. Min Act: -0.1700
Data Index: 545669 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4089. Min Act: -0.1700
Data Index: 3972440 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4089. Min Act: -0.1700
Data Index: 3839249 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4089. Min Act: -0.1700
Data Index: 2110082 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4714. Min Act: -0.1700
Data Index: 3765834 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4089. Min Act: -0.1700
Data Index: 2087179 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9089. Min Range: -9.9089
Max Act: 9.4089. Min Act: -0.1700
Data Index: 5822955 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19