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

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

Neuron 4345 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: 2.4872. Min Range: -2.4872

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1224979 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.4160. Min Act: -0.0000

Data Index: 1210165 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.4872. Min Act: -0.0000

Data Index: 808318 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.4004. Min Act: -0.0000

Data Index: 1218864 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.2191. Min Act: -0.0000

Data Index: 1178854 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.8773. Min Act: -0.0000

Data Index: 362537 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.2118. Min Act: -0.0000

Data Index: 319323 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.1452. Min Act: -0.0000

Data Index: 507515 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.1047. Min Act: -0.0000

Data Index: 794298 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.0935. Min Act: -0.0000

Data Index: 205145 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.9614. Min Act: -0.0000

Data Index: 92888 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1348471 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.0761. Min Act: -0.0000

Data Index: 518277 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.0448. Min Act: -0.0000

Data Index: 669394 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 2.4872. Min Range: -2.4872

Max Act: 2.2698. Min Act: -0.0000

Data Index: 539488 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.8422. Min Act: -0.0000

Data Index: 424183 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.8249. Min Act: -0.0000

Data Index: 847744 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.8659. Min Act: -0.0000

Data Index: 483651 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.7930. Min Act: -0.0000

Data Index: 375346 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.4872. Min Range: -2.4872

Max Act: 1.9027. Min Act: -0.0000

Data Index: 853342 (C4 (Web Text))

Max Activating Token Index: 662