Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0329. Min Range: -5.0329

Max Act: 5.0329. Min Act: -0.0001

Data Index: 632079 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.1955. Min Act: -0.0000

Data Index: 1273557 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.9656. Min Act: -0.0001

Data Index: 885357 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.6262. Min Act: -0.0000

Data Index: 1182829 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.1166. Min Act: -0.0000

Data Index: 599147 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.4114. Min Act: -0.0000

Data Index: 143057 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.6984. Min Act: -0.0000

Data Index: 209676 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.4617. Min Act: -0.0000

Data Index: 796131 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.7304. Min Act: -0.0001

Data Index: 335406 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.6192. Min Act: -0.0001

Data Index: 921326 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.6588. Min Act: -0.0001

Data Index: 94073 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.4381. Min Act: -0.0001

Data Index: 302504 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.8679. Min Act: -0.0001

Data Index: 340452 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.6785. Min Act: -0.0000

Data Index: 72458 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.5623. Min Act: -0.0001

Data Index: 57725 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.3604. Min Act: -0.0001

Data Index: 212777 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.3783. Min Act: -0.0000

Data Index: 786822 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.5039. Min Act: -0.0000

Data Index: 542774 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.4599. Min Act: -0.0001

Data Index: 389943 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 5.0329. Min Range: -5.0329

Max Act: 3.4812. Min Act: -0.0001

Data Index: 127900 (C4 (Web Text))

Max Activating Token Index: 6