Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1335 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.8522. Min Act: -0.0000

Data Index: 423344 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.8216. Min Act: -0.0000

Data Index: 312538 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.6376. Min Act: -0.0000

Data Index: 476949 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.5052. Min Act: -0.0000

Data Index: 281517 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.4929. Min Act: -0.0000

Data Index: 150229 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.4323. Min Act: -0.0000

Data Index: 1279177 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.3739. Min Act: -0.0000

Data Index: 260731 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.3560. Min Act: -0.0000

Data Index: 862056 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.5233. Min Act: -0.0000

Data Index: 302738 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.2430. Min Act: -0.0000

Data Index: 207313 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.0404. Min Act: -0.0000

Data Index: 149178 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.0431. Min Act: -0.0000

Data Index: 519854 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.3771. Min Act: -0.0000

Data Index: 602905 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.3406. Min Act: -0.0000

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.1655. Min Act: -0.0000

Data Index: 705155 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.1449. Min Act: -0.0000

Data Index: 1280517 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.1416. Min Act: -0.0000

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.0895. Min Act: -0.0000

Data Index: 971540 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 4.8522. Min Range: -4.8522

Max Act: 3.9253. Min Act: -0.0000

Data Index: 1231596 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 4.8522. Min Range: -4.8522

Max Act: 4.0425. Min Act: -0.0000

Data Index: 256377 (C4 (Web Text))

Max Activating Token Index: 997