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

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

Neuron 318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.3395. Min Act: -0.0001

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.1726. Min Act: -0.0000

Data Index: 814941 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0773. Min Act: -0.0000

Data Index: 234894 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0967. Min Act: -0.0001

Data Index: 1132495 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9888. Min Act: -0.0001

Data Index: 446751 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0238. Min Act: -0.0000

Data Index: 618473 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9443. Min Act: -0.0001

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0061. Min Act: -0.0000

Data Index: 825592 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9726. Min Act: -0.0000

Data Index: 905424 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9885. Min Act: -0.0000

Data Index: 745520 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0135. Min Act: -0.0000

Data Index: 478930 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1092935 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9852. Min Act: -0.0000

Data Index: 398220 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0033. Min Act: -0.0001

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1070013 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.3395. Min Range: -1.3395

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1029354 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9536. Min Act: -0.0000

Data Index: 306696 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9531. Min Act: -0.0000

Data Index: 857732 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9151. Min Act: -0.0000

Data Index: 477578 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.3395. Min Range: -1.3395

Max Act: 0.9556. Min Act: -0.0000

Data Index: 535707 (C4 (Web Text))

Max Activating Token Index: 747