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

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

Neuron 1161 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.6570. Min Act: -0.0000

Data Index: 994539 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1009865 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.6198. Min Act: -0.0000

Data Index: 669284 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.5708. Min Act: -0.0000

Data Index: 257546 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.5388. Min Act: -0.0000

Data Index: 918127 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.5511. Min Act: -0.0000

Data Index: 666919 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.5004. Min Act: -0.0000

Data Index: 44501 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4828. Min Act: -0.0000

Data Index: 258170 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4899. Min Act: -0.0000

Data Index: 649809 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1185898 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4422. Min Act: -0.0000

Data Index: 634632 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4112. Min Act: -0.0000

Data Index: 858611 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4323. Min Act: -0.0000

Data Index: 463647 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4153. Min Act: -0.0000

Data Index: 608248 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4187. Min Act: -0.0000

Data Index: 120119 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4253. Min Act: -0.0000

Data Index: 606400 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1335197 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.3800. Min Act: -0.0000

Data Index: 601844 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.4098. Min Act: -0.0000

Data Index: 542026 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.6570. Min Range: -0.6570

Max Act: 0.3876. Min Act: -0.0000

Data Index: 540354 (C4 (Web Text))

Max Activating Token Index: 576