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

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

Neuron 3457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0001

Data Index: 1028064 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4794. Min Act: -0.0001

Data Index: 141861 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4736. Min Act: -0.0000

Data Index: 161602 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4749. Min Act: -0.0000

Data Index: 131429 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4674. Min Act: -0.0000

Data Index: 588490 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4534. Min Act: -0.0000

Data Index: 159419 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4524. Min Act: -0.0001

Data Index: 410560 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4421. Min Act: -0.0001

Data Index: 1312656 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1212751 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4392. Min Act: -0.0001

Data Index: 975822 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4204. Min Act: -0.0001

Data Index: 292642 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4468. Min Act: -0.0001

Data Index: 560564 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4192. Min Act: -0.0000

Data Index: 590063 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4284. Min Act: -0.0001

Data Index: 1289688 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4374. Min Act: -0.0001

Data Index: 847878 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4192. Min Act: -0.0001

Data Index: 914828 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4178. Min Act: -0.0001

Data Index: 791541 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1285467 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4177. Min Act: -0.0001

Data Index: 1016294 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4008. Min Act: -0.0001

Data Index: 607965 (C4 (Web Text))

Max Activating Token Index: 131