Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1485 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1190473 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2473. Min Act: -0.0000

Data Index: 152112 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2101. Min Act: -0.0001

Data Index: 684283 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1875. Min Act: -0.0001

Data Index: 996487 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1840. Min Act: -0.0000

Data Index: 529449 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1725. Min Act: -0.0001

Data Index: 264842 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2016. Min Act: -0.0000

Data Index: 875230 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1162433 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1703. Min Act: -0.0000

Data Index: 109175 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1916. Min Act: -0.0000

Data Index: 830687 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1246673 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1270. Min Act: -0.0001

Data Index: 884631 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1239. Min Act: -0.0000

Data Index: 506088 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1318096 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1112631 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1562. Min Act: -0.0000

Data Index: 857381 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1388. Min Act: -0.0000

Data Index: 846419 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1448. Min Act: -0.0000

Data Index: 826335 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1470. Min Act: -0.0000

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1319. Min Act: -0.0001

Data Index: 833604 (C4 (Web Text))

Max Activating Token Index: 917