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

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

Neuron 4867 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.5328. Min Act: -0.0000

Data Index: 366266 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2249. Min Act: -0.0000

Data Index: 811006 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.2209. Min Act: -0.0000

Data Index: 526076 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 3.5328. Min Range: -3.5328

Max Act: 3.1674. Min Act: -0.0000

Data Index: 495872 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.9974. Min Act: -0.0000

Data Index: 178843 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7255. Min Act: -0.0000

Data Index: 1638068 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7456. Min Act: -0.0000

Data Index: 89292 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.9895. Min Act: -0.0000

Data Index: 1043859 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.5566. Min Act: -0.0000

Data Index: 609173 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.5588. Min Act: -0.0000

Data Index: 153547 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7862. Min Act: -0.0000

Data Index: 713261 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.6570. Min Act: -0.0000

Data Index: 919430 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.9281. Min Act: -0.0000

Data Index: 1336440 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7784. Min Act: -0.0000

Data Index: 1195775 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.5923. Min Act: -0.0000

Data Index: 1498882 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1334296 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.5264. Min Act: -0.0000

Data Index: 227114 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.8221. Min Act: -0.0000

Data Index: 205217 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.3868. Min Act: -0.0000

Data Index: 1580087 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 3.5328. Min Range: -3.5328

Max Act: 2.3775. Min Act: -0.0000

Data Index: 556928 (C4 (Web Text))

Max Activating Token Index: 187