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

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

Neuron 5109 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.4531. Min Act: -0.0002

Data Index: 1268991 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.4199. Min Act: -0.0002

Data Index: 1183633 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3795. Min Act: -0.0002

Data Index: 175434 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3919. Min Act: -0.0002

Data Index: 677331 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3789. Min Act: -0.0002

Data Index: 333555 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3777. Min Act: -0.0002

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3552. Min Act: -0.0002

Data Index: 1072495 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3616. Min Act: -0.0002

Data Index: 1249596 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3481. Min Act: -0.0002

Data Index: 543194 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3483. Min Act: -0.0002

Data Index: 642088 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3477. Min Act: -0.0002

Data Index: 213245 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3579. Min Act: -0.0002

Data Index: 1174444 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3365. Min Act: -0.0002

Data Index: 317906 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3362. Min Act: -0.0002

Data Index: 1164137 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3309. Min Act: -0.0002

Data Index: 1230470 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3296. Min Act: -0.0002

Data Index: 843707 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3274. Min Act: -0.0002

Data Index: 1004214 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3222. Min Act: -0.0002

Data Index: 1060166 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3091. Min Act: -0.0002

Data Index: 564897 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.4531. Min Range: -0.4531

Max Act: 0.3198. Min Act: -0.0002

Data Index: 832416 (C4 (Web Text))

Max Activating Token Index: 426