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

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

Neuron 4464 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1990. Min Range: -4.1990

Max Act: 4.1990. Min Act: -0.0000

Data Index: 559930 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 4.1990. Min Range: -4.1990

Max Act: 3.2625. Min Act: -0.0000

Data Index: 869333 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.9296. Min Act: -0.0000

Data Index: 255177 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.9291. Min Act: -0.0000

Data Index: 1262933 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.7564. Min Act: -0.0000

Data Index: 569059 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.5693. Min Act: -0.0000

Data Index: 335109 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.6746. Min Act: -0.0000

Data Index: 868391 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.5903. Min Act: -0.0000

Data Index: 358015 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4333. Min Act: -0.0000

Data Index: 674012 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4918. Min Act: -0.0000

Data Index: 891952 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4484. Min Act: -0.0000

Data Index: 302682 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.5597. Min Act: -0.0000

Data Index: 328658 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4260. Min Act: -0.0000

Data Index: 626629 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.3855. Min Act: -0.0000

Data Index: 748521 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4028. Min Act: -0.0000

Data Index: 61053 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4939. Min Act: -0.0000

Data Index: 413260 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1236182 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.3779. Min Act: -0.0000

Data Index: 928558 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.3628. Min Act: -0.0000

Data Index: 1025639 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 4.1990. Min Range: -4.1990

Max Act: 2.4802. Min Act: -0.0000

Data Index: 455954 (C4 (Web Text))

Max Activating Token Index: 5