Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1121 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0006

Data Index: 618194 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0295. Min Act: -0.0006

Data Index: 607098 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0292. Min Act: -0.0006

Data Index: 198377 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0283. Min Act: -0.0006

Data Index: 807895 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0278. Min Act: -0.0006

Data Index: 332633 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1327533 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0288. Min Act: -0.0006

Data Index: 837169 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0293. Min Act: -0.0006

Data Index: 390274 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0272. Min Act: -0.0006

Data Index: 434925 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1030297 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0285. Min Act: -0.0006

Data Index: 409811 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0264. Min Act: -0.0006

Data Index: 645373 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0281. Min Act: -0.0006

Data Index: 893994 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0257. Min Act: -0.0006

Data Index: 713386 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0268. Min Act: -0.0006

Data Index: 248303 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0272. Min Act: -0.0006

Data Index: 618982 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1149631 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1259122 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1133806 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1312126 (C4 (Web Text))

Max Activating Token Index: 318