Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1651 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0006

Data Index: 670282 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0331. Min Act: -0.0006

Data Index: 691760 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0006

Data Index: 524047 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0320. Min Act: -0.0006

Data Index: 301117 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1258080 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0323. Min Act: -0.0006

Data Index: 703780 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1064410 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0324. Min Act: -0.0006

Data Index: 855552 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0307. Min Act: -0.0006

Data Index: 1154490 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0317. Min Act: -0.0006

Data Index: 358519 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0303. Min Act: -0.0006

Data Index: 127810 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0262. Min Act: -0.0006

Data Index: 876865 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0291. Min Act: -0.0006

Data Index: 1344568 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0311. Min Act: -0.0006

Data Index: 315324 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0294. Min Act: -0.0006

Data Index: 7836 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0253. Min Act: -0.0006

Data Index: 512154 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1149270 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1082127 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0282. Min Act: -0.0006

Data Index: 647924 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0258. Min Act: -0.0006

Data Index: 61523 (C4 (Web Text))

Max Activating Token Index: 466