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

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

Neuron 3193 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1008337 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1172591 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1325. Min Act: -0.0000

Data Index: 286982 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1312. Min Act: -0.0000

Data Index: 429997 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1306. Min Act: -0.0000

Data Index: 690268 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1287. Min Act: -0.0000

Data Index: 847463 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1176034 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1154. Min Act: -0.0000

Data Index: 158345 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1229. Min Act: -0.0001

Data Index: 296620 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1284308 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1306. Min Act: -0.0000

Data Index: 720265 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1224. Min Act: -0.0001

Data Index: 440101 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1186. Min Act: -0.0000

Data Index: 874523 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1185. Min Act: -0.0001

Data Index: 869817 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1355463 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1169. Min Act: -0.0000

Data Index: 207504 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1161. Min Act: -0.0000

Data Index: 167522 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1087. Min Act: -0.0000

Data Index: 624366 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1112. Min Act: -0.0000

Data Index: 977077 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1083. Min Act: -0.0000

Data Index: 168684 (C4 (Web Text))

Max Activating Token Index: 444