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

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

Neuron 3368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.5394. Min Act: -0.0001

Data Index: 768395 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.5323. Min Act: -0.0001

Data Index: 356887 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4596. Min Act: -0.0001

Data Index: 82915 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4716. Min Act: -0.0001

Data Index: 55323 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4580. Min Act: -0.0001

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4347. Min Act: -0.0001

Data Index: 289625 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4376. Min Act: -0.0001

Data Index: 436508 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4340. Min Act: -0.0001

Data Index: 1159565 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4149. Min Act: -0.0001

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4126. Min Act: -0.0001

Data Index: 665413 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4359. Min Act: -0.0001

Data Index: 880258 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3953. Min Act: -0.0001

Data Index: 23371 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3951. Min Act: -0.0001

Data Index: 650129 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3969. Min Act: -0.0001

Data Index: 1236854 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4297. Min Act: -0.0001

Data Index: 284061 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3894. Min Act: -0.0001

Data Index: 28671 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4121. Min Act: -0.0001

Data Index: 107839 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1069388 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4048. Min Act: -0.0001

Data Index: 583578 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3973. Min Act: -0.0001

Data Index: 518353 (C4 (Web Text))

Max Activating Token Index: 825