Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8520. Min Act: -0.0001

Data Index: 145744 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.9031. Min Act: -0.0001

Data Index: 662385 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.9010. Min Act: -0.0001

Data Index: 573439 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8691. Min Act: -0.0001

Data Index: 1167036 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8957. Min Act: -0.0001

Data Index: 624557 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8584. Min Act: -0.0001

Data Index: 1193888 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8519. Min Act: -0.0001

Data Index: 413159 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8201. Min Act: -0.0001

Data Index: 525123 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8360. Min Act: -0.0001

Data Index: 331468 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1289165 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8380. Min Act: -0.0001

Data Index: 184713 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1003568 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7109. Min Act: -0.0001

Data Index: 28827 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7661. Min Act: -0.0001

Data Index: 910215 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8677. Min Act: -0.0001

Data Index: 600627 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7713. Min Act: -0.0001

Data Index: 427112 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1068583 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8585. Min Act: -0.0001

Data Index: 1068235 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8226. Min Act: -0.0001

Data Index: 285532 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7988. Min Act: -0.0001

Data Index: 617318 (C4 (Web Text))

Max Activating Token Index: 147