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

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

Neuron 3164 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4263. Min Act: -0.0002

Data Index: 894877 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4027. Min Act: -0.0002

Data Index: 466880 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3807. Min Act: -0.0001

Data Index: 864095 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3906. Min Act: -0.0002

Data Index: 492481 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4011. Min Act: -0.0002

Data Index: 678674 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3808. Min Act: -0.0002

Data Index: 664105 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1319621 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3882. Min Act: -0.0002

Data Index: 838706 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3819. Min Act: -0.0002

Data Index: 1092618 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3665. Min Act: -0.0002

Data Index: 910114 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3662. Min Act: -0.0002

Data Index: 471130 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3282. Min Act: -0.0002

Data Index: 169981 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3614. Min Act: -0.0001

Data Index: 88552 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3616. Min Act: -0.0002

Data Index: 439987 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3710. Min Act: -0.0001

Data Index: 692503 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3474. Min Act: -0.0001

Data Index: 594020 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3560. Min Act: -0.0001

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3506. Min Act: -0.0001

Data Index: 588325 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3623. Min Act: -0.0002

Data Index: 1057326 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1193519 (C4 (Web Text))

Max Activating Token Index: 813