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

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

Neuron 4848 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.9613. Min Act: -0.0000

Data Index: 963580 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1293499 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.2333. Min Act: -0.0000

Data Index: 241270 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.4125. Min Act: -0.0000

Data Index: 624546 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.1881. Min Act: -0.0000

Data Index: 246034 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1135073 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1205990 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9059. Min Act: -0.0000

Data Index: 189100 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9610. Min Act: -0.0000

Data Index: 294658 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9494. Min Act: -0.0000

Data Index: 754207 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9564. Min Act: -0.0000

Data Index: 892444 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1358779 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9457. Min Act: -0.0000

Data Index: 93989 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1124084 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.7428. Min Act: -0.0000

Data Index: 99465 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1332127 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1012457 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.8511. Min Act: -0.0000

Data Index: 712932 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.9613. Min Range: -1.9613

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1251440 (C4 (Web Text))

Max Activating Token Index: 383