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

Dataset: The Pile

Neuron 3620 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1285792 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1510. Min Act: -0.0000

Data Index: 221612 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1535. Min Act: -0.0000

Data Index: 612368 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1283411 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1302. Min Act: -0.0000

Data Index: 894618 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1991718 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1300. Min Act: -0.0000

Data Index: 159617 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1361411 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1269. Min Act: -0.0000

Data Index: 1284235 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1298. Min Act: -0.0000

Data Index: 794035 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1337029 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1239. Min Act: -0.0000

Data Index: 707749 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1226. Min Act: -0.0000

Data Index: 919059 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1890495 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1295. Min Act: -0.0000

Data Index: 377851 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1118. Min Act: -0.0000

Data Index: 628144 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1661371 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1572922 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1173. Min Act: -0.0000

Data Index: 178643 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1216. Min Act: -0.0000

Data Index: 841324 (The Pile)

Max Activating Token Index: 75