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

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

Neuron 4303 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0099. Min Range: -2.0099

Max Act: 2.0099. Min Act: -0.0000

Data Index: 30657 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3563. Min Act: -0.0000

Data Index: 307620 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.5135. Min Act: -0.0000

Data Index: 208663 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1344900 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1228497 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.7240. Min Act: -0.0000

Data Index: 256560 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.4815. Min Act: -0.0000

Data Index: 90883 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.4749. Min Act: -0.0000

Data Index: 665934 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1037151 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3686. Min Act: -0.0000

Data Index: 122456 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2880. Min Act: -0.0000

Data Index: 836563 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1214415 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2743. Min Act: -0.0000

Data Index: 735122 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2486. Min Act: -0.0000

Data Index: 490286 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.1942. Min Act: -0.0000

Data Index: 141492 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3275. Min Act: -0.0000

Data Index: 124062 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1244492 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2471. Min Act: -0.0000

Data Index: 212726 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2282. Min Act: -0.0000

Data Index: 675220 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1164899 (C4 (Web Text))

Max Activating Token Index: 814