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

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

Neuron 2578 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: 2.6099. Min Range: -2.6099

Max Act: 2.5466. Min Act: -0.0000

Data Index: 621243 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.5661. Min Act: -0.0000

Data Index: 287511 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.4184. Min Act: -0.0000

Data Index: 1027920 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.4029. Min Act: -0.0000

Data Index: 1319239 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.6099. Min Act: -0.0000

Data Index: 97250 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.5252. Min Act: -0.0000

Data Index: 227922 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.2982. Min Act: -0.0000

Data Index: 19562 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.2866. Min Act: -0.0000

Data Index: 355367 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.2103. Min Act: -0.0000

Data Index: 171718 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 2.6099. Min Range: -2.6099

Max Act: 1.8085. Min Act: -0.0000

Data Index: 423867 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.2200. Min Act: -0.0000

Data Index: 1296587 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.1566. Min Act: -0.0000

Data Index: 236649 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.1312. Min Act: -0.0000

Data Index: 915573 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 2.6099. Min Range: -2.6099

Max Act: 1.8897. Min Act: -0.0000

Data Index: 65603 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.1930. Min Act: -0.0000

Data Index: 57775 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.0677. Min Act: -0.0000

Data Index: 971239 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.0648. Min Act: -0.0000

Data Index: 196668 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 2.6099. Min Range: -2.6099

Max Act: 1.9350. Min Act: -0.0000

Data Index: 900739 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 2.6099. Min Range: -2.6099

Max Act: 2.0263. Min Act: -0.0000

Data Index: 859555 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 2.6099. Min Range: -2.6099

Max Act: 1.8962. Min Act: -0.0000

Data Index: 442564 (C4 (Web Text))

Max Activating Token Index: 895