Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1364 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.7528. Min Act: -0.0001

Data Index: 439356 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6492. Min Act: -0.0001

Data Index: 339066 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6190. Min Act: -0.0001

Data Index: 264096 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5796. Min Act: -0.0001

Data Index: 552523 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5794. Min Act: -0.0001

Data Index: 695543 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5463. Min Act: -0.0001

Data Index: 329491 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4599. Min Act: -0.0001

Data Index: 202349 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5299. Min Act: -0.0001

Data Index: 507777 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1251031 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5061. Min Act: -0.0001

Data Index: 994620 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1107992 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5250. Min Act: -0.0001

Data Index: 1161555 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5433. Min Act: -0.0001

Data Index: 560770 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5410. Min Act: -0.0001

Data Index: 488686 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5226. Min Act: -0.0001

Data Index: 604760 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4872. Min Act: -0.0001

Data Index: 1009558 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5157. Min Act: -0.0001

Data Index: 923886 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5160. Min Act: -0.0001

Data Index: 972899 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5015. Min Act: -0.0001

Data Index: 1011066 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1047661 (C4 (Web Text))

Max Activating Token Index: 405