Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1956. Min Act: -0.0001

Data Index: 620458 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1101010 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1402. Min Act: -0.0001

Data Index: 526085 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1327. Min Act: -0.0001

Data Index: 933378 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1268. Min Act: -0.0001

Data Index: 263479 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1393. Min Act: -0.0001

Data Index: 368783 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1391. Min Act: -0.0001

Data Index: 283162 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1053055 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1257. Min Act: -0.0001

Data Index: 563190 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1252. Min Act: -0.0001

Data Index: 479454 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1204634 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1242. Min Act: -0.0001

Data Index: 633544 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1191. Min Act: -0.0001

Data Index: 642365 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1216878 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1203. Min Act: -0.0001

Data Index: 302558 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1152. Min Act: -0.0001

Data Index: 275400 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1013280 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1046. Min Act: -0.0001

Data Index: 521839 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1043948 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1956. Min Range: -0.1956

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1233066 (C4 (Web Text))

Max Activating Token Index: 87