Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3290 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0398. Min Act: -0.0003

Data Index: 375420 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0395. Min Act: -0.0003

Data Index: 247969 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0328. Min Act: -0.0003

Data Index: 89623 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1103175 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1250535 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0359. Min Act: -0.0003

Data Index: 235602 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0323. Min Act: -0.0003

Data Index: 115987 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0357. Min Act: -0.0003

Data Index: 462563 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1324059 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0331. Min Act: -0.0003

Data Index: 659300 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0335. Min Act: -0.0003

Data Index: 12328 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1338403 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0327. Min Act: -0.0003

Data Index: 597339 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1341690 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1147249 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1448628 (Python Code)

Max Activating Token Index: 834

Text #16

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0320. Min Act: -0.0003

Data Index: 699297 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0370. Min Act: -0.0003

Data Index: 192028 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1096115 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0398. Min Range: -0.0398

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1321056 (C4 (Web Text))

Max Activating Token Index: 248