Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0426. Min Act: -0.0002

Data Index: 894548 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0405. Min Act: -0.0002

Data Index: 695242 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1326013 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0359. Min Act: -0.0001

Data Index: 661235 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0373. Min Act: -0.0002

Data Index: 613699 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1215901 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1344580 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0369. Min Act: -0.0001

Data Index: 1257526 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0366. Min Act: -0.0001

Data Index: 107952 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0337. Min Act: -0.0002

Data Index: 543245 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0359. Min Act: -0.0002

Data Index: 268051 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0361. Min Act: -0.0001

Data Index: 136635 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1024384 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0360. Min Act: -0.0002

Data Index: 68300 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0349. Min Act: -0.0002

Data Index: 708617 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0350. Min Act: -0.0002

Data Index: 340747 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0348. Min Act: -0.0002

Data Index: 189811 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1252822 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0320. Min Act: -0.0001

Data Index: 96453 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0279. Min Act: -0.0002

Data Index: 133904 (C4 (Web Text))

Max Activating Token Index: 935