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

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

Neuron 3442 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: 0.2985. Min Range: -0.2985

Max Act: 0.2985. Min Act: -0.0001

Data Index: 28792 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2975. Min Act: -0.0001

Data Index: 1212489 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2780. Min Act: -0.0001

Data Index: 545266 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2628. Min Act: -0.0001

Data Index: 26401 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2817. Min Act: -0.0001

Data Index: 65007 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1282264 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2806. Min Act: -0.0001

Data Index: 783221 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2568. Min Act: -0.0001

Data Index: 944303 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1235615 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2633. Min Act: -0.0001

Data Index: 52478 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2639. Min Act: -0.0001

Data Index: 825663 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2416. Min Act: -0.0001

Data Index: 186834 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2383. Min Act: -0.0001

Data Index: 1288660 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2664. Min Act: -0.0001

Data Index: 992022 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2533. Min Act: -0.0001

Data Index: 350114 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2526. Min Act: -0.0001

Data Index: 557279 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2345. Min Act: -0.0001

Data Index: 947861 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1070804 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1244457 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2323. Min Act: -0.0001

Data Index: 967965 (C4 (Web Text))

Max Activating Token Index: 955