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

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

Neuron 4477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0002

Data Index: 607878 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1443108 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1384001 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1271304 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1521595 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1403471 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0468. Min Act: -0.0002

Data Index: 624167 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1552846 (Python Code)

Max Activating Token Index: 300

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0458. Min Act: -0.0002

Data Index: 981189 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1422925 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0473. Min Act: -0.0002

Data Index: 194548 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1385587 (Python Code)

Max Activating Token Index: 313

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1610012 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1451284 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1372449 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0445. Min Act: -0.0002

Data Index: 289904 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1247878 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0406. Min Act: -0.0002

Data Index: 771437 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1597340 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1390918 (Python Code)

Max Activating Token Index: 324