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

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

Neuron 3256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1440515 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.5119. Min Act: -0.0000

Data Index: 984311 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4523. Min Act: -0.0000

Data Index: 1090444 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1128715 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1482985 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1494926 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1042062 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2245. Min Act: -0.0000

Data Index: 1571438 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.1429. Min Act: -0.0000

Data Index: 509610 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2897. Min Act: -0.0000

Data Index: 811805 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2656. Min Act: -0.0000

Data Index: 1032854 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2607. Min Act: -0.0000

Data Index: 1240635 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1170411 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2036. Min Act: -0.0000

Data Index: 203063 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1549120 (Python Code)

Max Activating Token Index: 299

Text #15

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2395. Min Act: -0.0000

Data Index: 96458 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1120729 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1228430 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1459040 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 1.5462. Min Range: -1.5462

Max Act: 1.2128. Min Act: -0.0000

Data Index: 587434 (C4 (Web Text))

Max Activating Token Index: 97