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

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

Neuron 437 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0328. Min Act: -0.0002

Data Index: 264449 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 250087 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0320. Min Act: -0.0003

Data Index: 196894 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1212660 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0296. Min Act: -0.0002

Data Index: 761762 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0293. Min Act: -0.0003

Data Index: 964001 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1311079 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1471150 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0286. Min Act: -0.0003

Data Index: 695555 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0264. Min Act: -0.0003

Data Index: 876354 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0272. Min Act: -0.0003

Data Index: 393633 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0261. Min Act: -0.0002

Data Index: 95763 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1570970 (Python Code)

Max Activating Token Index: 756

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0267. Min Act: -0.0003

Data Index: 416207 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1059417 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0308. Min Act: -0.0003

Data Index: 437031 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1235816 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0292. Min Act: -0.0003

Data Index: 189717 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0003

Data Index: 895653 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1405974 (Python Code)

Max Activating Token Index: 442