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

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

Neuron 23 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: 0.2129. Min Range: -0.2129

Max Act: 0.2129. Min Act: -0.0000

Data Index: 325302 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1638. Min Act: -0.0001

Data Index: 397493 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1064027 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1638. Min Act: -0.0000

Data Index: 528266 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1185363 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1090768 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1209512 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1384. Min Act: -0.0000

Data Index: 138762 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1426. Min Act: -0.0000

Data Index: 906677 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1195567 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1066692 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1323. Min Act: -0.0001

Data Index: 401688 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1378. Min Act: -0.0000

Data Index: 563325 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1301989 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1318. Min Act: -0.0001

Data Index: 848507 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1346. Min Act: -0.0001

Data Index: 194450 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1134519 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1308. Min Act: -0.0000

Data Index: 472965 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1184637 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.2129. Min Range: -0.2129

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1150440 (C4 (Web Text))

Max Activating Token Index: 797