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

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

Neuron 261 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0958. Min Range: -1.0958

Max Act: 1.0958. Min Act: -0.0001

Data Index: 765576 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.9222. Min Act: -0.0001

Data Index: 1162283 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8912. Min Act: -0.0001

Data Index: 1093609 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8845. Min Act: -0.0001

Data Index: 1204893 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8377. Min Act: -0.0001

Data Index: 596987 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7908. Min Act: -0.0001

Data Index: 886022 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8100. Min Act: -0.0001

Data Index: 1319757 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7579. Min Act: -0.0001

Data Index: 929196 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1099923 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.8177. Min Act: -0.0001

Data Index: 997024 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1120183 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7912. Min Act: -0.0001

Data Index: 792539 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7614. Min Act: -0.0001

Data Index: 113352 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1325612 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7378. Min Act: -0.0001

Data Index: 1072946 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7476. Min Act: -0.0001

Data Index: 824889 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7290. Min Act: -0.0001

Data Index: 3778 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1190564 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7484. Min Act: -0.0001

Data Index: 560442 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.0958. Min Range: -1.0958

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1050327 (C4 (Web Text))

Max Activating Token Index: 195