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

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

Neuron 4017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0651. Min Range: -2.0651

Max Act: 2.0651. Min Act: -0.0000

Data Index: 69641 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.4280. Min Act: -0.0000

Data Index: 46049 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1055705 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1234192 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2866. Min Act: -0.0000

Data Index: 778159 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.3635. Min Act: -0.0000

Data Index: 736518 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2428. Min Act: -0.0000

Data Index: 319884 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1358568 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2465. Min Act: -0.0000

Data Index: 873297 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1481. Min Act: -0.0000

Data Index: 383472 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2159. Min Act: -0.0000

Data Index: 266699 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1373. Min Act: -0.0000

Data Index: 6337 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1317168 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1127397 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1535. Min Act: -0.0000

Data Index: 531885 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1081761 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1742. Min Act: -0.0000

Data Index: 515315 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1350. Min Act: -0.0000

Data Index: 437954 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1193. Min Act: -0.0000

Data Index: 359767 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 2.0651. Min Range: -2.0651

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1046059 (C4 (Web Text))

Max Activating Token Index: 185