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

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

Neuron 842 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.9824. Min Act: -0.0000

Data Index: 231888 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.7803. Min Act: -0.0000

Data Index: 540921 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.7547. Min Act: -0.0000

Data Index: 1246822 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.5494. Min Act: -0.0000

Data Index: 584974 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.6267. Min Act: -0.0000

Data Index: 41801 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.5192. Min Act: -0.0000

Data Index: 276502 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.4228. Min Act: -0.0000

Data Index: 513835 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.4113. Min Act: -0.0001

Data Index: 220911 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1300174 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.4085. Min Act: -0.0001

Data Index: 1170423 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.3723. Min Act: -0.0000

Data Index: 684165 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.1612. Min Act: -0.0000

Data Index: 324294 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.3528. Min Act: -0.0000

Data Index: 387836 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.3486. Min Act: -0.0001

Data Index: 661520 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.3235. Min Act: -0.0001

Data Index: 762069 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.4189. Min Act: -0.0001

Data Index: 305756 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.4443. Min Act: -0.0000

Data Index: 351544 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.2190. Min Act: -0.0001

Data Index: 529101 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.3404. Min Act: -0.0000

Data Index: 496842 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.9824. Min Range: -2.9824

Max Act: 2.3160. Min Act: -0.0000

Data Index: 917390 (C4 (Web Text))

Max Activating Token Index: 784