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

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

Neuron 2658 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0001

Data Index: 835980 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0277. Min Act: -0.0001

Data Index: 43424 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1186085 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0259. Min Act: -0.0001

Data Index: 380270 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0263. Min Act: -0.0001

Data Index: 274452 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0229. Min Act: -0.0001

Data Index: 342337 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0240. Min Act: -0.0001

Data Index: 422479 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0232. Min Act: -0.0001

Data Index: 851379 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0240. Min Act: -0.0001

Data Index: 752753 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1329048 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0214. Min Act: -0.0000

Data Index: 498088 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0230. Min Act: -0.0001

Data Index: 872357 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0227. Min Act: -0.0001

Data Index: 257622 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0219. Min Act: -0.0000

Data Index: 140295 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0225. Min Act: -0.0000

Data Index: 1313089 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0209. Min Act: -0.0001

Data Index: 464744 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1182708 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0205. Min Act: -0.0000

Data Index: 434093 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0202. Min Act: -0.0001

Data Index: 1112322 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0189. Min Act: -0.0000

Data Index: 201687 (C4 (Web Text))

Max Activating Token Index: 539