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

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

Neuron 3854 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.3354. Min Act: -0.0001

Data Index: 293208 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1159725 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.3058. Min Act: -0.0001

Data Index: 678454 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1226580 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2915. Min Act: -0.0001

Data Index: 1276085 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2729. Min Act: -0.0001

Data Index: 543392 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2756. Min Act: -0.0001

Data Index: 151615 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2622. Min Act: -0.0001

Data Index: 823437 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2593. Min Act: -0.0001

Data Index: 549841 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2691. Min Act: -0.0001

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2644. Min Act: -0.0001

Data Index: 906638 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2466. Min Act: -0.0001

Data Index: 1066425 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2434. Min Act: -0.0001

Data Index: 513397 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2446. Min Act: -0.0001

Data Index: 748662 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1304167 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2502. Min Act: -0.0001

Data Index: 624096 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2200. Min Act: -0.0001

Data Index: 642963 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2262. Min Act: -0.0001

Data Index: 620036 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2091. Min Act: -0.0001

Data Index: 261595 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2244. Min Act: -0.0001

Data Index: 737550 (C4 (Web Text))

Max Activating Token Index: 618