Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1973 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0004

Data Index: 1056348 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0342. Min Act: -0.0004

Data Index: 415517 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0327. Min Act: -0.0004

Data Index: 612777 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0299. Min Act: -0.0005

Data Index: 156386 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0307. Min Act: -0.0004

Data Index: 166102 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0286. Min Act: -0.0004

Data Index: 132023 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0297. Min Act: -0.0005

Data Index: 143572 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0299. Min Act: -0.0004

Data Index: 564133 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0287. Min Act: -0.0005

Data Index: 1266245 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0291. Min Act: -0.0005

Data Index: 580703 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0291. Min Act: -0.0005

Data Index: 505022 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0289. Min Act: -0.0005

Data Index: 154234 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0286. Min Act: -0.0005

Data Index: 394907 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0286. Min Act: -0.0005

Data Index: 585810 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0273. Min Act: -0.0004

Data Index: 83754 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0284. Min Act: -0.0005

Data Index: 420030 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0289. Min Act: -0.0005

Data Index: 947618 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1149919 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0274. Min Act: -0.0005

Data Index: 611870 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0280. Min Act: -0.0004

Data Index: 334763 (C4 (Web Text))

Max Activating Token Index: 899