Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1211911 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1544. Min Act: -0.0000

Data Index: 246311 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1517363 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1421. Min Act: -0.0000

Data Index: 232927 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1457. Min Act: -0.0000

Data Index: 752188 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1559570 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1367. Min Act: -0.0000

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1223761 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1359. Min Act: -0.0000

Data Index: 356027 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1285. Min Act: -0.0000

Data Index: 730566 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1259. Min Act: -0.0000

Data Index: 918440 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1274. Min Act: -0.0000

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1300. Min Act: -0.0000

Data Index: 113046 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1539678 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1212. Min Act: -0.0000

Data Index: 125628 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1633340 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1063295 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1241. Min Act: -0.0000

Data Index: 449006 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1049212 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1455945 (Python Code)

Max Activating Token Index: 648