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

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

Neuron 2731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0001

Data Index: 205610 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1378. Min Act: -0.0000

Data Index: 881687 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1411. Min Act: -0.0000

Data Index: 618506 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1335. Min Act: -0.0001

Data Index: 584034 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1319. Min Act: -0.0001

Data Index: 418401 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1248. Min Act: -0.0000

Data Index: 765787 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1001424 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1252. Min Act: -0.0000

Data Index: 32268 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1259. Min Act: -0.0001

Data Index: 609189 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1076902 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1187567 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1331349 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1013224 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1225534 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1170. Min Act: -0.0001

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1159. Min Act: -0.0000

Data Index: 232471 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1239. Min Act: -0.0001

Data Index: 178182 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1159. Min Act: -0.0000

Data Index: 638756 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1179. Min Act: -0.0001

Data Index: 700402 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1179. Min Act: -0.0001

Data Index: 759766 (C4 (Web Text))

Max Activating Token Index: 850