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

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

Neuron 5897 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7541. Min Range: -3.7541

Max Act: 3.7541. Min Act: -0.0001

Data Index: 1186860 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.7541. Min Range: -3.7541

Max Act: 3.0459. Min Act: -0.0001

Data Index: 9031 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.7274. Min Act: -0.0001

Data Index: 949049 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.8883. Min Act: -0.0001

Data Index: 1150088 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.7883. Min Act: -0.0001

Data Index: 566011 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 3.7541. Min Range: -3.7541

Max Act: 3.1281. Min Act: -0.0001

Data Index: 835487 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.9970. Min Act: -0.0001

Data Index: 582268 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 3.7541. Min Range: -3.7541

Max Act: 3.1892. Min Act: -0.0001

Data Index: 496341 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.9983. Min Act: -0.0001

Data Index: 767397 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.9907. Min Act: -0.0001

Data Index: 378682 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.9808. Min Act: -0.0001

Data Index: 222477 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.6270. Min Act: -0.0001

Data Index: 911901 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.8768. Min Act: -0.0001

Data Index: 1211199 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.6396. Min Act: -0.0001

Data Index: 562138 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.7559. Min Act: -0.0001

Data Index: 293287 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.4542. Min Act: -0.0001

Data Index: 438476 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.7277. Min Act: -0.0001

Data Index: 180842 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.4297. Min Act: -0.0001

Data Index: 1284610 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.3627. Min Act: -0.0001

Data Index: 48863 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 3.7541. Min Range: -3.7541

Max Act: 2.2212. Min Act: -0.0001

Data Index: 628028 (C4 (Web Text))

Max Activating Token Index: 43