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

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

Neuron 1547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0005

Data Index: 1181357 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0283. Min Act: -0.0005

Data Index: 594937 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1274592 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0290. Min Act: -0.0005

Data Index: 428199 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0295. Min Act: -0.0005

Data Index: 539469 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0292. Min Act: -0.0005

Data Index: 69692 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0005

Data Index: 503138 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1503212 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0275. Min Act: -0.0005

Data Index: 1413710 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0281. Min Act: -0.0005

Data Index: 1262990 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0284. Min Act: -0.0005

Data Index: 158626 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0272. Min Act: -0.0005

Data Index: 765289 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0272. Min Act: -0.0005

Data Index: 869650 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1067518 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0268. Min Act: -0.0005

Data Index: 447255 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0261. Min Act: -0.0005

Data Index: 441059 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1273105 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0257. Min Act: -0.0005

Data Index: 298878 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0262. Min Act: -0.0005

Data Index: 47357 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0260. Min Act: -0.0005

Data Index: 991184 (C4 (Web Text))

Max Activating Token Index: 210