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

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

Neuron 3335 in Layer 8

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: 858678 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0302. Min Act: -0.0000

Data Index: 1312596 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0312. Min Act: 0.0001

Data Index: 707176 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0294. Min Act: 0.0002

Data Index: 929471 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0290. Min Act: 0.0001

Data Index: 304670 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0298. Min Act: 0.0001

Data Index: 990324 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0286. Min Act: -0.0000

Data Index: 189796 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0257. Min Act: 0.0002

Data Index: 1322362 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0272. Min Act: 0.0000

Data Index: 306780 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0271. Min Act: 0.0001

Data Index: 895131 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: 0.0001

Data Index: 730719 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0260. Min Act: 0.0001

Data Index: 538673 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0269. Min Act: 0.0001

Data Index: 272164 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0267. Min Act: 0.0000

Data Index: 464589 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0266. Min Act: -0.0000

Data Index: 1188147 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0265. Min Act: 0.0004

Data Index: 1318510 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0260. Min Act: 0.0001

Data Index: 401358 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0270. Min Act: 0.0001

Data Index: 780085 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0249. Min Act: 0.0001

Data Index: 170323 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0247. Min Act: 0.0000

Data Index: 1250520 (C4 (Web Text))

Max Activating Token Index: 636