Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3850 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.6817. Min Act: -0.0000

Data Index: 649884 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.5131. Min Act: -0.0000

Data Index: 1277240 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.4501. Min Act: -0.0000

Data Index: 392024 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1285250 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3794. Min Act: -0.0000

Data Index: 647481 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.4663. Min Act: -0.0000

Data Index: 688269 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3486. Min Act: -0.0000

Data Index: 782154 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.3502. Min Act: -0.0000

Data Index: 241475 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2005. Min Act: -0.0000

Data Index: 182296 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2776. Min Act: -0.0000

Data Index: 642487 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2422. Min Act: -0.0000

Data Index: 898063 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1062581 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2127. Min Act: -0.0000

Data Index: 814990 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2210. Min Act: -0.0000

Data Index: 900263 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2146. Min Act: -0.0000

Data Index: 876860 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1314697 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1188236 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1082147 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.1932. Min Act: -0.0000

Data Index: 26022 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.6817. Min Range: -1.6817

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1305087 (C4 (Web Text))

Max Activating Token Index: 705