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

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

Neuron 4616 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: 1.5953. Min Range: -1.5953

Max Act: 1.5953. Min Act: -0.0000

Data Index: 127282 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.5206. Min Act: -0.0000

Data Index: 1028691 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1067606 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.4000. Min Act: -0.0000

Data Index: 125061 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.3410. Min Act: -0.0000

Data Index: 511158 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.2596. Min Act: -0.0000

Data Index: 81002 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.3317. Min Act: -0.0000

Data Index: 729453 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1252990 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.3573. Min Act: -0.0000

Data Index: 807466 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.1869. Min Act: -0.0000

Data Index: 381049 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.3253. Min Act: -0.0000

Data Index: 898977 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.2493. Min Act: -0.0000

Data Index: 567954 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.1048. Min Act: -0.0000

Data Index: 695220 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1052303 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.2275. Min Act: -0.0000

Data Index: 87364 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.1532. Min Act: -0.0000

Data Index: 153817 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1321557 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1100241 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.2126. Min Act: -0.0000

Data Index: 386050 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.5953. Min Range: -1.5953

Max Act: 1.2036. Min Act: -0.0000

Data Index: 304302 (C4 (Web Text))

Max Activating Token Index: 874