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

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

Neuron 3835 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: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0002

Data Index: 409119 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1487610 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1225148 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1423753 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1497378 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1382847 (Python Code)

Max Activating Token Index: 633

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1503123 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1411027 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1597859 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1259266 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1339173 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1586697 (Python Code)

Max Activating Token Index: 422

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1529340 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1405678 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1649074 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1423154 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1165152 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0299. Min Act: -0.0002

Data Index: 245032 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1451780 (Python Code)

Max Activating Token Index: 810

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0325. Min Act: -0.0002

Data Index: 251741 (C4 (Web Text))

Max Activating Token Index: 1005