Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2844 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1012838 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3524. Min Act: -0.0000

Data Index: 800523 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.3083. Min Act: -0.0000

Data Index: 157319 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2744. Min Act: -0.0000

Data Index: 348311 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1308313 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2749. Min Act: -0.0000

Data Index: 599604 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1048014 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1102061 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1059438 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2619. Min Act: -0.0000

Data Index: 113617 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2606. Min Act: 0.0000

Data Index: 591841 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1213992 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2498. Min Act: -0.0000

Data Index: 657150 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2483. Min Act: -0.0000

Data Index: 981842 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2456. Min Act: -0.0000

Data Index: 607838 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2528. Min Act: -0.0000

Data Index: 988725 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1253047 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1142242 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2590. Min Act: -0.0000

Data Index: 21049 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.3761. Min Range: -0.3761

Max Act: 0.2406. Min Act: -0.0000

Data Index: 51516 (C4 (Web Text))

Max Activating Token Index: 96