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

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

Neuron 3731 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: 1.8879. Min Range: -1.8879

Max Act: 1.8879. Min Act: -0.0000

Data Index: 950003 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.5519. Min Act: -0.0000

Data Index: 298006 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.5412. Min Act: -0.0000

Data Index: 418103 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4721. Min Act: -0.0000

Data Index: 392863 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4680. Min Act: -0.0000

Data Index: 863066 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3804. Min Act: -0.0000

Data Index: 529388 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3237. Min Act: -0.0001

Data Index: 850359 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.4639. Min Act: -0.0000

Data Index: 581229 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3837. Min Act: -0.0000

Data Index: 835494 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.2618. Min Act: -0.0000

Data Index: 573711 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.2560. Min Act: -0.0000

Data Index: 665839 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3186. Min Act: -0.0000

Data Index: 335367 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1196618 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.3142. Min Act: -0.0000

Data Index: 467086 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.1383. Min Act: -0.0000

Data Index: 900462 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.1324. Min Act: -0.0000

Data Index: 820306 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.1801. Min Act: -0.0000

Data Index: 611138 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.0824. Min Act: -0.0000

Data Index: 611232 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.1164. Min Act: -0.0000

Data Index: 168362 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.8879. Min Range: -1.8879

Max Act: 1.0961. Min Act: -0.0000

Data Index: 510433 (C4 (Web Text))

Max Activating Token Index: 617