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

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

Neuron 3029 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6471. Min Range: -3.6471

Max Act: 3.6471. Min Act: -0.0001

Data Index: 791716 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 3.6471. Min Range: -3.6471

Max Act: 3.0796. Min Act: -0.0001

Data Index: 470034 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 3.6471. Min Range: -3.6471

Max Act: 3.1973. Min Act: -0.0001

Data Index: 14147 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 3.6471. Min Range: -3.6471

Max Act: 3.1557. Min Act: -0.0001

Data Index: 626697 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.8026. Min Act: -0.0001

Data Index: 619086 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.7504. Min Act: -0.0001

Data Index: 915043 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.6202. Min Act: 0.0000

Data Index: 469542 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.8553. Min Act: -0.0001

Data Index: 408939 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.7765. Min Act: -0.0001

Data Index: 110004 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.6481. Min Act: -0.0001

Data Index: 1213549 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.6170. Min Act: -0.0001

Data Index: 429013 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.5853. Min Act: -0.0001

Data Index: 704580 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.5553. Min Act: -0.0001

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.4393. Min Act: -0.0001

Data Index: 301436 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.4926. Min Act: -0.0001

Data Index: 753653 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.4878. Min Act: -0.0001

Data Index: 103527 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.4757. Min Act: -0.0001

Data Index: 947838 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.3261. Min Act: -0.0001

Data Index: 1041621 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.4271. Min Act: -0.0001

Data Index: 564431 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 3.6471. Min Range: -3.6471

Max Act: 2.4245. Min Act: -0.0001

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 162