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

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

Neuron 2342 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3869. Min Act: -0.0001

Data Index: 503555 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.4230. Min Act: -0.0001

Data Index: 15393 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1019081 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3469. Min Act: -0.0001

Data Index: 34749 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3859. Min Act: -0.0001

Data Index: 47597 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.4109. Min Act: -0.0001

Data Index: 60562 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3556. Min Act: -0.0001

Data Index: 565492 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1027120 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3556. Min Act: -0.0001

Data Index: 339554 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3672. Min Act: -0.0001

Data Index: 401734 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3349. Min Act: -0.0001

Data Index: 818971 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3501. Min Act: -0.0001

Data Index: 48453 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1536850 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1093741 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1255262 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3421. Min Act: -0.0001

Data Index: 178443 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3296. Min Act: -0.0001

Data Index: 495409 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3190. Min Act: -0.0001

Data Index: 858864 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3386. Min Act: -0.0001

Data Index: 890714 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1503458 (Python Code)

Max Activating Token Index: 1016