Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4657. Min Act: -0.0001

Data Index: 993587 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4844. Min Act: -0.0001

Data Index: 823752 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1297729 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4834. Min Act: -0.0001

Data Index: 1222647 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4667. Min Act: -0.0001

Data Index: 448693 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4429. Min Act: -0.0001

Data Index: 1017930 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4749. Min Act: -0.0001

Data Index: 303161 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4264. Min Act: -0.0001

Data Index: 99929 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0001

Data Index: 804562 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4180. Min Act: -0.0001

Data Index: 922101 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1342497 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4129. Min Act: -0.0001

Data Index: 989913 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1155801 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3983. Min Act: -0.0001

Data Index: 284715 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4229. Min Act: -0.0001

Data Index: 57564 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3918. Min Act: -0.0001

Data Index: 1082956 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4314. Min Act: -0.0001

Data Index: 1207153 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3880. Min Act: -0.0001

Data Index: 84932 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3997. Min Act: -0.0001

Data Index: 1328340 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4371. Min Act: -0.0001

Data Index: 107368 (C4 (Web Text))

Max Activating Token Index: 560