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

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

Neuron 4174 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 90155 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0312. Min Act: -0.0003

Data Index: 262847 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0271. Min Act: -0.0003

Data Index: 16673 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0003

Data Index: 518569 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0245. Min Act: -0.0003

Data Index: 938713 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0249. Min Act: -0.0002

Data Index: 763691 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0237. Min Act: -0.0003

Data Index: 148723 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0226. Min Act: -0.0002

Data Index: 209496 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1096630 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0223. Min Act: -0.0003

Data Index: 17403 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0223. Min Act: -0.0003

Data Index: 309909 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0216. Min Act: -0.0002

Data Index: 469050 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0215. Min Act: -0.0002

Data Index: 506606 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0215. Min Act: -0.0002

Data Index: 570865 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1274452 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0210. Min Act: -0.0002

Data Index: 133464 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1193908 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0211. Min Act: -0.0003

Data Index: 550677 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0210. Min Act: -0.0003

Data Index: 121964 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0202. Min Act: -0.0003

Data Index: 218735 (C4 (Web Text))

Max Activating Token Index: 1