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

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

Neuron 86 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: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0001

Data Index: 507714 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0362. Min Act: -0.0001

Data Index: 405428 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1374573 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0342. Min Act: -0.0001

Data Index: 158080 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1645994 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0328. Min Act: -0.0001

Data Index: 36531 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1617354 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1190961 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0312. Min Act: -0.0001

Data Index: 172068 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1535570 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1442210 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1477261 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1571386 (Python Code)

Max Activating Token Index: 164

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0292. Min Act: -0.0001

Data Index: 779891 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0313. Min Act: -0.0001

Data Index: 455891 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1382154 (Python Code)

Max Activating Token Index: 597

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1555363 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0277. Min Act: -0.0001

Data Index: 435455 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1570184 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0304. Min Act: -0.0001

Data Index: 704830 (C4 (Web Text))

Max Activating Token Index: 911