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

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

Neuron 1324 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: 0.5426. Min Range: -0.5426

Max Act: 0.5334. Min Act: -0.0001

Data Index: 100067 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5426. Min Act: -0.0001

Data Index: 94587 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5197. Min Act: -0.0001

Data Index: 818759 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4915. Min Act: -0.0001

Data Index: 959793 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4543. Min Act: -0.0001

Data Index: 621928 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1032079 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4630. Min Act: -0.0001

Data Index: 161848 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4615. Min Act: -0.0001

Data Index: 256190 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4473. Min Act: -0.0001

Data Index: 126821 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4329. Min Act: -0.0001

Data Index: 804661 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4330. Min Act: -0.0001

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4198. Min Act: -0.0001

Data Index: 556501 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4305. Min Act: -0.0001

Data Index: 789764 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3967. Min Act: -0.0001

Data Index: 1233789 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4403. Min Act: -0.0001

Data Index: 286713 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4078. Min Act: -0.0001

Data Index: 169023 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4365. Min Act: -0.0001

Data Index: 667113 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4205. Min Act: -0.0000

Data Index: 396393 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4069. Min Act: -0.0001

Data Index: 1174036 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4158. Min Act: -0.0001

Data Index: 1219525 (C4 (Web Text))

Max Activating Token Index: 302