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

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

Neuron 2799 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.4514. Min Act: -0.0001

Data Index: 829590 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3259. Min Act: -0.0001

Data Index: 912164 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0957. Min Act: -0.0000

Data Index: 933180 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1252. Min Act: -0.0001

Data Index: 1115650 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1427. Min Act: -0.0001

Data Index: 788211 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.2034. Min Act: -0.0000

Data Index: 274817 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.2742. Min Act: -0.0001

Data Index: 88938 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1732. Min Act: -0.0001

Data Index: 713437 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.2047. Min Act: -0.0001

Data Index: 979697 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1594. Min Act: -0.0001

Data Index: 358109 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1631. Min Act: -0.0000

Data Index: 967097 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1242. Min Act: -0.0001

Data Index: 1210940 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9656. Min Act: -0.0001

Data Index: 826432 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9097. Min Act: -0.0001

Data Index: 898837 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0361. Min Act: -0.0001

Data Index: 585775 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0595. Min Act: -0.0000

Data Index: 5100 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0195. Min Act: -0.0001

Data Index: 181358 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1247995 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1039470 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0975. Min Act: -0.0001

Data Index: 456788 (C4 (Web Text))

Max Activating Token Index: 63