Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 405 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1565. Min Act: -0.0002

Data Index: 444891 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1462. Min Act: -0.0002

Data Index: 619556 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1500. Min Act: -0.0002

Data Index: 612457 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1119743 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1468. Min Act: -0.0002

Data Index: 552435 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1405. Min Act: -0.0002

Data Index: 218668 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1309. Min Act: -0.0002

Data Index: 999220 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1338. Min Act: -0.0002

Data Index: 805494 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1271. Min Act: -0.0002

Data Index: 736228 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1310. Min Act: -0.0002

Data Index: 28218 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1266. Min Act: -0.0002

Data Index: 569554 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1041304 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1020716 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1174. Min Act: -0.0002

Data Index: 538231 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1226756 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1238. Min Act: -0.0002

Data Index: 872658 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1259. Min Act: -0.0001

Data Index: 218373 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1195. Min Act: -0.0002

Data Index: 154584 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1250. Min Act: -0.0002

Data Index: 80316 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1118. Min Act: -0.0002

Data Index: 334655 (C4 (Web Text))

Max Activating Token Index: 871