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

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

Neuron 1578 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: 0.7318. Min Range: -0.7318

Max Act: 0.7318. Min Act: -0.0002

Data Index: 1042438 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6953. Min Act: -0.0002

Data Index: 1380111 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7125. Min Act: -0.0002

Data Index: 766569 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6678. Min Act: -0.0002

Data Index: 555792 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7029. Min Act: -0.0002

Data Index: 1163387 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7031. Min Act: -0.0002

Data Index: 79897 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6412. Min Act: -0.0002

Data Index: 567022 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6613. Min Act: -0.0002

Data Index: 1050670 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6529. Min Act: -0.0002

Data Index: 649080 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7145. Min Act: -0.0002

Data Index: 554090 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.7203. Min Act: -0.0002

Data Index: 353935 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6659. Min Act: -0.0002

Data Index: 1512752 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6657. Min Act: -0.0002

Data Index: 1420459 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6597. Min Act: -0.0002

Data Index: 256831 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6802. Min Act: -0.0002

Data Index: 1436219 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6795. Min Act: -0.0002

Data Index: 21260 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6613. Min Act: -0.0002

Data Index: 572048 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6860. Min Act: -0.0002

Data Index: 1047014 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6283. Min Act: -0.0002

Data Index: 64815 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.7318. Min Range: -0.7318

Max Act: 0.6874. Min Act: -0.0002

Data Index: 1112932 (C4 (Web Text))

Max Activating Token Index: 771