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

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

Neuron 3176 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: 1.3364. Min Range: -1.3364

Max Act: 1.3364. Min Act: -0.0000

Data Index: 308838 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.2092. Min Act: -0.0000

Data Index: 385807 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.2285. Min Act: -0.0000

Data Index: 729134 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1701. Min Act: -0.0000

Data Index: 654490 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.2042. Min Act: -0.0000

Data Index: 51002 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1453. Min Act: -0.0000

Data Index: 93636 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0823. Min Act: -0.0000

Data Index: 34005 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1348. Min Act: -0.0000

Data Index: 148368 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1474. Min Act: -0.0000

Data Index: 662222 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1131548 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0908. Min Act: -0.0000

Data Index: 344972 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0824. Min Act: -0.0000

Data Index: 449316 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.1098. Min Act: -0.0000

Data Index: 321911 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1210213 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0121. Min Act: -0.0000

Data Index: 359070 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0353. Min Act: -0.0000

Data Index: 315046 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0079. Min Act: -0.0000

Data Index: 233621 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0646. Min Act: -0.0000

Data Index: 540084 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0337. Min Act: -0.0000

Data Index: 3258 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0261. Min Act: -0.0000

Data Index: 224718 (C4 (Web Text))

Max Activating Token Index: 379