Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1402 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1275898 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1209952 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0406. Min Act: -0.0002

Data Index: 970522 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0361. Min Act: -0.0002

Data Index: 200153 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0359. Min Act: -0.0002

Data Index: 838234 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0355. Min Act: -0.0002

Data Index: 898616 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0328. Min Act: -0.0002

Data Index: 735657 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1099874 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0338. Min Act: -0.0002

Data Index: 656223 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1172760 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0327. Min Act: -0.0002

Data Index: 658948 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0319. Min Act: -0.0002

Data Index: 715345 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0325. Min Act: -0.0002

Data Index: 997270 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0311. Min Act: -0.0002

Data Index: 631963 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0309. Min Act: -0.0002

Data Index: 46951 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0314. Min Act: -0.0002

Data Index: 385036 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1002709 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0300. Min Act: -0.0002

Data Index: 463778 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0303. Min Act: -0.0002

Data Index: 966882 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0547. Min Range: -0.0547

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1207809 (C4 (Web Text))

Max Activating Token Index: 233