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

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

Neuron 1351 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: 4.1503. Min Range: -4.1503

Max Act: 4.1503. Min Act: -0.0000

Data Index: 771010 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.4249. Min Act: -0.0000

Data Index: 1048682 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.5020. Min Act: -0.0000

Data Index: 965602 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.3296. Min Act: -0.0000

Data Index: 677926 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.2647. Min Act: -0.0000

Data Index: 1031390 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.2335. Min Act: -0.0000

Data Index: 1151913 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.1982. Min Act: -0.0000

Data Index: 1344415 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 4.1503. Min Range: -4.1503

Max Act: 3.1478. Min Act: -0.0000

Data Index: 1136166 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.9780. Min Act: -0.0000

Data Index: 68376 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.9056. Min Act: -0.0000

Data Index: 1328060 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.9666. Min Act: -0.0000

Data Index: 680479 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.8256. Min Act: -0.0000

Data Index: 215217 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.9445. Min Act: -0.0000

Data Index: 257845 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.7025. Min Act: -0.0000

Data Index: 666045 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.6601. Min Act: -0.0000

Data Index: 441628 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.6488. Min Act: -0.0000

Data Index: 1269002 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.7741. Min Act: -0.0000

Data Index: 1247299 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.7689. Min Act: -0.0000

Data Index: 988550 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.7770. Min Act: -0.0000

Data Index: 669853 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 4.1503. Min Range: -4.1503

Max Act: 2.6169. Min Act: -0.0000

Data Index: 788697 (C4 (Web Text))

Max Activating Token Index: 409