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

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

Neuron 1871 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3458. Min Act: -0.0001

Data Index: 296385 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3799. Min Act: -0.0001

Data Index: 930593 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1075184 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3364. Min Act: -0.0001

Data Index: 82760 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1062023 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3229. Min Act: -0.0001

Data Index: 625610 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2983. Min Act: -0.0001

Data Index: 318776 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3232. Min Act: -0.0001

Data Index: 1162993 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.3171. Min Act: -0.0001

Data Index: 1228537 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2947. Min Act: -0.0001

Data Index: 395242 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2681. Min Act: -0.0001

Data Index: 140334 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2831. Min Act: -0.0001

Data Index: 735058 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2684. Min Act: -0.0001

Data Index: 1265075 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.1748. Min Act: -0.0001

Data Index: 853258 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2480. Min Act: -0.0001

Data Index: 520930 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2252. Min Act: -0.0001

Data Index: 1033247 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2295. Min Act: -0.0001

Data Index: 325198 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2664. Min Act: -0.0001

Data Index: 847013 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2336. Min Act: -0.0001

Data Index: 347767 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.3799. Min Range: -0.3799

Max Act: 0.2490. Min Act: -0.0001

Data Index: 136668 (C4 (Web Text))

Max Activating Token Index: 643