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

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

Neuron 2105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.7483. Min Act: -0.0000

Data Index: 646113 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.5164. Min Act: -0.0000

Data Index: 545004 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4193. Min Act: -0.0001

Data Index: 871598 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1086635 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4115. Min Act: -0.0000

Data Index: 818616 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.4048. Min Act: -0.0001

Data Index: 1090195 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3923. Min Act: -0.0000

Data Index: 29921 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1093663 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3745. Min Act: -0.0000

Data Index: 797946 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3549. Min Act: -0.0001

Data Index: 930029 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3522. Min Act: -0.0000

Data Index: 214095 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3546. Min Act: -0.0000

Data Index: 750251 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1348495 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1215335 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3480. Min Act: -0.0000

Data Index: 228943 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1200227 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3349. Min Act: -0.0000

Data Index: 731707 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1103345 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3454. Min Act: -0.0001

Data Index: 1342891 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.7483. Min Range: -0.7483

Max Act: 0.3304. Min Act: -0.0001

Data Index: 1353270 (C4 (Web Text))

Max Activating Token Index: 215