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

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

Neuron 4784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.4473. Min Act: -0.0000

Data Index: 435833 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1335742 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.3165. Min Act: -0.0000

Data Index: 185976 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.2153. Min Act: -0.0000

Data Index: 920018 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1342177 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1733. Min Act: -0.0000

Data Index: 700093 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1481. Min Act: -0.0000

Data Index: 586467 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0988. Min Act: -0.0000

Data Index: 499081 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.1484. Min Act: -0.0000

Data Index: 952068 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0386. Min Act: -0.0000

Data Index: 754433 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0325. Min Act: -0.0000

Data Index: 331083 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1351139 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9943. Min Act: -0.0000

Data Index: 897783 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9775. Min Act: -0.0000

Data Index: 582280 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1299402 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9719. Min Act: -0.0000

Data Index: 369535 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.4473. Min Range: -1.4473

Max Act: 1.0319. Min Act: -0.0000

Data Index: 709450 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.8939. Min Act: -0.0000

Data Index: 828055 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9319. Min Act: -0.0000

Data Index: 690767 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.4473. Min Range: -1.4473

Max Act: 0.9861. Min Act: -0.0000

Data Index: 993237 (C4 (Web Text))

Max Activating Token Index: 356