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

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

Neuron 5538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.4530. Min Act: -0.0000

Data Index: 39134 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1107967 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.2572. Min Act: -0.0000

Data Index: 278290 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.2485. Min Act: -0.0000

Data Index: 826953 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.2197. Min Act: -0.0000

Data Index: 509832 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.2756. Min Act: -0.0000

Data Index: 704611 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.2324. Min Act: -0.0000

Data Index: 846404 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0724. Min Act: -0.0000

Data Index: 516783 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0681. Min Act: -0.0000

Data Index: 675048 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0345. Min Act: -0.0000

Data Index: 944162 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0565. Min Act: -0.0000

Data Index: 67543 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0516. Min Act: -0.0000

Data Index: 406049 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.4530. Min Range: -1.4530

Max Act: 0.9849. Min Act: -0.0000

Data Index: 526222 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0318. Min Act: -0.0000

Data Index: 702265 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.4530. Min Range: -1.4530

Max Act: 1.0043. Min Act: -0.0000

Data Index: 578874 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 1.4530. Min Range: -1.4530

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1030387 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 1.4530. Min Range: -1.4530

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1092725 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.4530. Min Range: -1.4530

Max Act: 0.9475. Min Act: -0.0000

Data Index: 496834 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.4530. Min Range: -1.4530

Max Act: 0.8807. Min Act: -0.0000

Data Index: 570742 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.4530. Min Range: -1.4530

Max Act: 0.8919. Min Act: -0.0000

Data Index: 52330 (C4 (Web Text))

Max Activating Token Index: 757