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

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

Neuron 581 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: 0.9773. Min Range: -0.9773

Max Act: 0.9773. Min Act: 0.0001

Data Index: 69425 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.9079. Min Act: -0.0000

Data Index: 222564 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.8340. Min Act: -0.0000

Data Index: 128810 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7930. Min Act: 0.0001

Data Index: 91048 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7695. Min Act: 0.0000

Data Index: 88607 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7813. Min Act: -0.0000

Data Index: 587529 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7695. Min Act: -0.0000

Data Index: 729245 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7209. Min Act: 0.0001

Data Index: 176781 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7613. Min Act: -0.0000

Data Index: 705163 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7332. Min Act: 0.0001

Data Index: 348261 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7746. Min Act: -0.0000

Data Index: 797733 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7644. Min Act: -0.0000

Data Index: 315419 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7354. Min Act: 0.0000

Data Index: 113360 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7110. Min Act: 0.0001

Data Index: 1135965 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7140. Min Act: 0.0001

Data Index: 636928 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7169. Min Act: -0.0000

Data Index: 807796 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1320953 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.6780. Min Act: -0.0000

Data Index: 375894 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1067565 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.9773. Min Range: -0.9773

Max Act: 0.7070. Min Act: -0.0000

Data Index: 82031 (C4 (Web Text))

Max Activating Token Index: 770