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

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

Neuron 3913 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.7005. Min Act: -0.0001

Data Index: 585009 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6810. Min Act: -0.0000

Data Index: 349265 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.7177. Min Act: -0.0001

Data Index: 771898 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6558. Min Act: -0.0000

Data Index: 285653 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6784. Min Act: -0.0000

Data Index: 591123 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6759. Min Act: -0.0001

Data Index: 275231 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6551. Min Act: -0.0001

Data Index: 130840 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6165. Min Act: -0.0000

Data Index: 434467 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6161. Min Act: -0.0001

Data Index: 231059 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1225449 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1315436 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5854. Min Act: -0.0001

Data Index: 128031 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5832. Min Act: -0.0001

Data Index: 632000 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5995. Min Act: -0.0001

Data Index: 104859 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5791. Min Act: -0.0001

Data Index: 43754 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5851. Min Act: -0.0000

Data Index: 989927 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5650. Min Act: -0.0001

Data Index: 1029743 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5729. Min Act: -0.0001

Data Index: 950662 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5412. Min Act: -0.0001

Data Index: 578878 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.7177. Min Range: -0.7177

Max Act: 0.5452. Min Act: -0.0001

Data Index: 253133 (C4 (Web Text))

Max Activating Token Index: 726