Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.7281. Min Act: -0.0000

Data Index: 989195 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.7444. Min Act: -0.0000

Data Index: 606320 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.6743. Min Act: -0.0000

Data Index: 367462 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5709. Min Act: -0.0000

Data Index: 468947 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.6517. Min Act: -0.0000

Data Index: 560157 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5954. Min Act: -0.0000

Data Index: 216761 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.6303. Min Act: -0.0000

Data Index: 894846 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.6007. Min Act: -0.0000

Data Index: 348977 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1272401 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5954. Min Act: -0.0000

Data Index: 818193 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5722. Min Act: -0.0000

Data Index: 508224 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5628. Min Act: -0.0000

Data Index: 838355 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5571. Min Act: -0.0000

Data Index: 157511 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1039118 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5256. Min Act: -0.0000

Data Index: 768019 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.4994. Min Act: -0.0000

Data Index: 460093 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5691. Min Act: -0.0000

Data Index: 933517 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5303. Min Act: -0.0000

Data Index: 390295 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5307. Min Act: -0.0000

Data Index: 99835 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.7444. Min Range: -0.7444

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1117002 (C4 (Web Text))

Max Activating Token Index: 9