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

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

Neuron 886 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: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0004

Data Index: 949329 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0345. Min Act: -0.0004

Data Index: 1579577 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0317. Min Act: -0.0004

Data Index: 989630 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1530573 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0317. Min Act: -0.0004

Data Index: 859440 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1514574 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0314. Min Act: -0.0004

Data Index: 852576 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0260. Min Act: -0.0004

Data Index: 706553 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0250. Min Act: -0.0004

Data Index: 840988 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0266. Min Act: -0.0004

Data Index: 916674 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0276. Min Act: -0.0004

Data Index: 1643564 (Python Code)

Max Activating Token Index: 674

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0281. Min Act: -0.0004

Data Index: 1387815 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1078230 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0271. Min Act: -0.0004

Data Index: 556127 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0285. Min Act: -0.0004

Data Index: 438737 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1430798 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0264. Min Act: -0.0004

Data Index: 1318333 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1458360 (Python Code)

Max Activating Token Index: 284

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1192457 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1606713 (Python Code)

Max Activating Token Index: 262