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

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

Neuron 3254 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: 0.0299. Min Range: -0.0299

Max Act: 0.0296. Min Act: -0.0003

Data Index: 69229 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1371344 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1499645 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1466435 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0267. Min Act: -0.0003

Data Index: 995253 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1562892 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0003

Data Index: 262319 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0275. Min Act: -0.0003

Data Index: 393404 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1538606 (Python Code)

Max Activating Token Index: 636

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0244. Min Act: -0.0003

Data Index: 671814 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0265. Min Act: -0.0003

Data Index: 158843 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0260. Min Act: -0.0004

Data Index: 1538559 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1104382 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1434382 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1425163 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0240. Min Act: -0.0003

Data Index: 453550 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1376608 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1458733 (Python Code)

Max Activating Token Index: 559

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0254. Min Act: -0.0003

Data Index: 487025 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0244. Min Act: -0.0003

Data Index: 122100 (C4 (Web Text))

Max Activating Token Index: 920