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

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

Neuron 1749 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1585324 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0759. Min Act: -0.0002

Data Index: 820083 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1309388 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1240859 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1139337 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1622373 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0736. Min Act: -0.0002

Data Index: 844505 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0684. Min Act: -0.0002

Data Index: 650257 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0704. Min Act: -0.0002

Data Index: 701285 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0759. Min Act: -0.0002

Data Index: 798745 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0728. Min Act: -0.0002

Data Index: 628392 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0698. Min Act: -0.0002

Data Index: 161886 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0726. Min Act: -0.0002

Data Index: 435017 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0618. Min Act: -0.0002

Data Index: 971502 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1337131 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1121179 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0734. Min Act: -0.0002

Data Index: 282581 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0725. Min Act: -0.0002

Data Index: 113244 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0647. Min Act: -0.0002

Data Index: 184789 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0662. Min Act: -0.0002

Data Index: 821077 (C4 (Web Text))

Max Activating Token Index: 410