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

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

Neuron 3075 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: 0.0403. Min Range: -0.0403

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1081964 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0348. Min Act: -0.0001

Data Index: 169762 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1626604 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0340. Min Act: -0.0001

Data Index: 140948 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0338. Min Act: -0.0001

Data Index: 316221 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1570437 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1451182 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1532025 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0312. Min Act: -0.0001

Data Index: 629268 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0313. Min Act: -0.0001

Data Index: 527907 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1474102 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0315. Min Act: -0.0001

Data Index: 972078 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1526495 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0296. Min Act: -0.0001

Data Index: 414248 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0312. Min Act: -0.0001

Data Index: 631630 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0276. Min Act: -0.0001

Data Index: 726399 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0294. Min Act: -0.0001

Data Index: 145300 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0267. Min Act: -0.0001

Data Index: 93538 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1361461 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.0403. Min Range: -0.0403

Max Act: 0.0296. Min Act: -0.0001

Data Index: 624037 (C4 (Web Text))

Max Activating Token Index: 80