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

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

Neuron 1294 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0002

Data Index: 23747 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0002

Data Index: 420900 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0032. Min Act: -0.0002

Data Index: 382279 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0032. Min Act: -0.0002

Data Index: 702916 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1644048 (Python Code)

Max Activating Token Index: 659

Text #5

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 746233 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 37204 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 356582 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 484119 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 520743 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0002

Data Index: 803047 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 1640074 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 1184447 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0002

Data Index: 1449240 (Python Code)

Max Activating Token Index: 532

Text #14

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1206452 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 730836 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 650420 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 70461 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1284685 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1086919 (C4 (Web Text))

Max Activating Token Index: 704