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

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

Neuron 2000 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: 0.1432. Min Range: -0.1432

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1235597 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1432. Min Act: -0.0001

Data Index: 377616 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1376. Min Act: -0.0001

Data Index: 523722 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1185546 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1352. Min Act: -0.0001

Data Index: 489034 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1362. Min Act: -0.0001

Data Index: 179338 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1346. Min Act: -0.0001

Data Index: 715376 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1290. Min Act: -0.0001

Data Index: 996667 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1128211 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1278. Min Act: -0.0001

Data Index: 211854 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1200428 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1316. Min Act: -0.0001

Data Index: 680868 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1255269 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1160473 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1293. Min Act: -0.0001

Data Index: 248172 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1237. Min Act: -0.0001

Data Index: 267778 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1254. Min Act: -0.0001

Data Index: 157579 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1240. Min Act: -0.0001

Data Index: 637118 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1285. Min Act: -0.0001

Data Index: 667302 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1273. Min Act: -0.0001

Data Index: 852909 (C4 (Web Text))

Max Activating Token Index: 24