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

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

Neuron 2018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3457. Min Act: -0.0000

Data Index: 250768 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1132216 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2707. Min Act: -0.0000

Data Index: 887640 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2678. Min Act: -0.0000

Data Index: 418860 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2646. Min Act: -0.0000

Data Index: 61657 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2761. Min Act: -0.0000

Data Index: 923838 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2685. Min Act: -0.0000

Data Index: 700102 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2767. Min Act: -0.0000

Data Index: 555607 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2337. Min Act: -0.0000

Data Index: 994303 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2580. Min Act: -0.0000

Data Index: 474774 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2471. Min Act: -0.0000

Data Index: 310059 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2466. Min Act: -0.0000

Data Index: 432571 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2403. Min Act: -0.0000

Data Index: 179188 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2303. Min Act: -0.0000

Data Index: 600455 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2475. Min Act: -0.0000

Data Index: 696068 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1038224 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1126926 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2327. Min Act: -0.0000

Data Index: 718210 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1204212 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2397. Min Act: -0.0000

Data Index: 26732 (C4 (Web Text))

Max Activating Token Index: 875