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

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

Neuron 3015 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3266. Min Range: -4.3266

Max Act: 4.3266. Min Act: -0.0000

Data Index: 825870 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 4.3266. Min Range: -4.3266

Max Act: 4.2883. Min Act: -0.0000

Data Index: 98027 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.7865. Min Act: -0.0000

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.6086. Min Act: -0.0000

Data Index: 724525 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.4015. Min Act: -0.0000

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.3062. Min Act: -0.0000

Data Index: 896096 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.2844. Min Act: -0.0000

Data Index: 1175595 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 4.3266. Min Range: -4.3266

Max Act: 3.5694. Min Act: -0.0000

Data Index: 1173456 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.9051. Min Act: -0.0000

Data Index: 208850 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.6626. Min Act: -0.0000

Data Index: 819831 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.5689. Min Act: -0.0000

Data Index: 43232 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.5519. Min Act: -0.0000

Data Index: 583112 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.5469. Min Act: -0.0000

Data Index: 643400 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.5976. Min Act: -0.0000

Data Index: 128302 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.5250. Min Act: -0.0000

Data Index: 1073493 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.3759. Min Act: -0.0000

Data Index: 71507 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.3319. Min Act: -0.0000

Data Index: 312777 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.5601. Min Act: -0.0000

Data Index: 1340775 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.4377. Min Act: -0.0000

Data Index: 520692 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 4.3266. Min Range: -4.3266

Max Act: 2.3554. Min Act: -0.0000

Data Index: 429662 (C4 (Web Text))

Max Activating Token Index: 123