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

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

Neuron 1600 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1886. Min Act: -0.0001

Data Index: 943120 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1292144 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1561. Min Act: -0.0001

Data Index: 291348 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1362. Min Act: -0.0001

Data Index: 172413 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1340028 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1333. Min Act: -0.0001

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1329. Min Act: -0.0001

Data Index: 785809 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1195. Min Act: -0.0001

Data Index: 131791 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1146. Min Act: -0.0001

Data Index: 427455 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1263. Min Act: -0.0001

Data Index: 900253 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1114536 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1209. Min Act: -0.0001

Data Index: 791805 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1272. Min Act: -0.0001

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1218531 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1195433 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1294. Min Act: -0.0001

Data Index: 85511 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1234. Min Act: -0.0001

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1267. Min Act: -0.0001

Data Index: 47438 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1289405 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.1886. Min Range: -0.1886

Max Act: 0.1206. Min Act: -0.0001

Data Index: 569883 (C4 (Web Text))

Max Activating Token Index: 79