Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1646315 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0417. Min Act: -0.0000

Data Index: 886231 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0365. Min Act: -0.0000

Data Index: 894160 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0326. Min Act: -0.0000

Data Index: 901528 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0349. Min Act: -0.0000

Data Index: 564829 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1016597 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1535143 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0300. Min Act: -0.0000

Data Index: 22767 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0299. Min Act: -0.0000

Data Index: 413251 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1371325 (Python Code)

Max Activating Token Index: 783

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0267. Min Act: -0.0000

Data Index: 560935 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0268. Min Act: -0.0000

Data Index: 1593693 (Python Code)

Max Activating Token Index: 844

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0268. Min Act: -0.0000

Data Index: 1295199 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0269. Min Act: -0.0000

Data Index: 652991 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1404959 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0269. Min Act: -0.0000

Data Index: 608275 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0266. Min Act: -0.0000

Data Index: 88793 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0263. Min Act: -0.0000

Data Index: 833215 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0273. Min Act: -0.0000

Data Index: 998309 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0245. Min Act: -0.0000

Data Index: 877206 (C4 (Web Text))

Max Activating Token Index: 597