Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0001

Data Index: 1157052 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5103. Min Act: -0.0000

Data Index: 134251 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5483. Min Act: -0.0001

Data Index: 1261556 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5479. Min Act: -0.0000

Data Index: 596295 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5162. Min Act: -0.0001

Data Index: 151558 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4986. Min Act: -0.0001

Data Index: 1273721 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4412. Min Act: -0.0001

Data Index: 790315 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4404. Min Act: -0.0000

Data Index: 537800 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4797. Min Act: -0.0000

Data Index: 409348 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4551. Min Act: -0.0000

Data Index: 639837 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4538. Min Act: -0.0001

Data Index: 996071 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4361. Min Act: -0.0001

Data Index: 1249141 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4209. Min Act: -0.0001

Data Index: 1219475 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3766. Min Act: -0.0000

Data Index: 27430 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4066. Min Act: -0.0001

Data Index: 736234 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3904. Min Act: -0.0000

Data Index: 34764 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4410. Min Act: -0.0001

Data Index: 25173 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4240. Min Act: -0.0000

Data Index: 17908 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4538. Min Act: -0.0001

Data Index: 1345204 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4314. Min Act: -0.0001

Data Index: 225425 (C4 (Web Text))

Max Activating Token Index: 985