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

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

Neuron 3079 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: 0.3575. Min Range: -0.3575

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1221051 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3575. Min Act: -0.0000

Data Index: 567736 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3398. Min Act: -0.0000

Data Index: 241210 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1510452 (Python Code)

Max Activating Token Index: 583

Text #4

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1589879 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1550000 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3149. Min Act: -0.0000

Data Index: 756238 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3161. Min Act: -0.0000

Data Index: 721225 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3240. Min Act: -0.0000

Data Index: 934847 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1046472 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2960. Min Act: -0.0000

Data Index: 375467 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3010. Min Act: -0.0000

Data Index: 629322 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1099595 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2854. Min Act: -0.0000

Data Index: 441505 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2965. Min Act: -0.0000

Data Index: 840215 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2967. Min Act: -0.0000

Data Index: 798520 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2834. Min Act: -0.0000

Data Index: 490286 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1414826 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1220741 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2883. Min Act: -0.0000

Data Index: 339588 (C4 (Web Text))

Max Activating Token Index: 70