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

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

Neuron 3169 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: 0.1624. Min Range: -0.1624

Max Act: 0.1624. Min Act: -0.0000

Data Index: 44260 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1468. Min Act: -0.0000

Data Index: 545394 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1346. Min Act: -0.0000

Data Index: 359547 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1440. Min Act: -0.0001

Data Index: 297179 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1421. Min Act: -0.0000

Data Index: 981168 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1244573 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1160623 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1291. Min Act: -0.0000

Data Index: 756725 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1289. Min Act: -0.0000

Data Index: 108989 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1321. Min Act: -0.0000

Data Index: 227153 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1262. Min Act: 0.0000

Data Index: 442796 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1006119 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1277. Min Act: -0.0001

Data Index: 409273 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1340518 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1193. Min Act: -0.0000

Data Index: 932010 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1122736 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1332384 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1046483 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1017677 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1212. Min Act: -0.0000

Data Index: 531401 (C4 (Web Text))

Max Activating Token Index: 537