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

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

Neuron 4420 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2686. Min Range: -3.2686

Max Act: 3.0389. Min Act: -0.0000

Data Index: 819672 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 3.2686. Min Range: -3.2686

Max Act: 3.0168. Min Act: -0.0000

Data Index: 1234021 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.9624. Min Act: -0.0000

Data Index: 625964 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.9355. Min Act: -0.0000

Data Index: 1062001 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.9745. Min Act: -0.0000

Data Index: 100239 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.1943. Min Act: -0.0000

Data Index: 36598 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.8439. Min Act: -0.0000

Data Index: 1067798 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.8568. Min Act: -0.0000

Data Index: 441562 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.8563. Min Act: -0.0000

Data Index: 107930 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.2686. Min Range: -3.2686

Max Act: 3.2686. Min Act: -0.0000

Data Index: 1164826 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.7691. Min Act: -0.0000

Data Index: 47428 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.8084. Min Act: -0.0000

Data Index: 655791 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.9645. Min Act: -0.0000

Data Index: 1136030 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.6408. Min Act: -0.0000

Data Index: 933761 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.8666. Min Act: -0.0000

Data Index: 1016048 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.6159. Min Act: -0.0000

Data Index: 346903 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.7006. Min Act: -0.0000

Data Index: 1292260 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.7942. Min Act: -0.0000

Data Index: 661283 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.9371. Min Act: -0.0000

Data Index: 1285530 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 3.2686. Min Range: -3.2686

Max Act: 2.8704. Min Act: -0.0000

Data Index: 982357 (C4 (Web Text))

Max Activating Token Index: 1007