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

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

Neuron 3331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4267. Min Act: -0.0000

Data Index: 881913 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1179779 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4428. Min Act: -0.0001

Data Index: 168916 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3961. Min Act: -0.0001

Data Index: 155125 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1243457 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.4174. Min Act: -0.0001

Data Index: 1357915 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3462. Min Act: -0.0001

Data Index: 65262 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3815. Min Act: -0.0000

Data Index: 188111 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1212071 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3910. Min Act: -0.0001

Data Index: 334601 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3772. Min Act: -0.0001

Data Index: 72782 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3498. Min Act: -0.0000

Data Index: 363990 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3606. Min Act: -0.0001

Data Index: 378814 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1109217 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3770. Min Act: -0.0000

Data Index: 154104 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3467. Min Act: -0.0000

Data Index: 312130 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3877. Min Act: -0.0001

Data Index: 707338 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3541. Min Act: -0.0001

Data Index: 230343 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3630. Min Act: -0.0000

Data Index: 119469 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.4428. Min Range: -0.4428

Max Act: 0.3866. Min Act: -0.0001

Data Index: 650176 (C4 (Web Text))

Max Activating Token Index: 793