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

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

Neuron 1787 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.4345. Min Act: -0.0000

Data Index: 798085 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.4300. Min Act: -0.0000

Data Index: 79321 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.3979. Min Act: -0.0000

Data Index: 335036 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2384. Min Act: -0.0000

Data Index: 316058 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1515968 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1304781 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2450. Min Act: -0.0000

Data Index: 549489 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2322. Min Act: -0.0000

Data Index: 7073 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2200. Min Act: -0.0000

Data Index: 613482 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2186. Min Act: -0.0000

Data Index: 49463 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1061668 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1144. Min Act: -0.0000

Data Index: 11878 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1971. Min Act: -0.0000

Data Index: 82563 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1801. Min Act: -0.0000

Data Index: 543635 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1472038 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1077706 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1793. Min Act: -0.0000

Data Index: 762228 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2517. Min Act: -0.0000

Data Index: 750524 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1523. Min Act: -0.0000

Data Index: 529582 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2243. Min Act: -0.0000

Data Index: 227439 (C4 (Web Text))

Max Activating Token Index: 426