Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1754 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0236. Min Act: -0.0004

Data Index: 550986 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0241. Min Act: -0.0004

Data Index: 707275 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0236. Min Act: -0.0004

Data Index: 569740 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0238. Min Act: -0.0004

Data Index: 639461 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0223. Min Act: -0.0004

Data Index: 894120 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0228. Min Act: -0.0004

Data Index: 26828 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1276887 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0232. Min Act: -0.0004

Data Index: 372840 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0219. Min Act: -0.0004

Data Index: 567127 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0240. Min Act: -0.0004

Data Index: 650633 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0221. Min Act: -0.0004

Data Index: 598348 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0192. Min Act: -0.0004

Data Index: 555576 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0214. Min Act: -0.0004

Data Index: 266792 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0199. Min Act: -0.0004

Data Index: 905970 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1058272 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0215. Min Act: -0.0004

Data Index: 1019964 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1471489 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1212406 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1257484 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0225. Min Act: -0.0004

Data Index: 213349 (C4 (Web Text))

Max Activating Token Index: 496