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

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

Neuron 490 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8912. Min Range: -5.8912

Max Act: 5.8912. Min Act: -0.0000

Data Index: 922471 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 5.8912. Min Range: -5.8912

Max Act: 5.6212. Min Act: -0.0000

Data Index: 877382 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 5.8912. Min Range: -5.8912

Max Act: 5.5580. Min Act: -0.0000

Data Index: 273274 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 5.8912. Min Range: -5.8912

Max Act: 4.8435. Min Act: -0.0000

Data Index: 871562 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 5.8912. Min Range: -5.8912

Max Act: 4.7838. Min Act: -0.0000

Data Index: 193708 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 5.8912. Min Range: -5.8912

Max Act: 4.3764. Min Act: -0.0000

Data Index: 1080697 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 5.8912. Min Range: -5.8912

Max Act: 4.0929. Min Act: -0.0000

Data Index: 367306 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.8861. Min Act: -0.0000

Data Index: 58073 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.8511. Min Act: -0.0000

Data Index: 1183942 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.8319. Min Act: -0.0000

Data Index: 1183426 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.8397. Min Act: -0.0000

Data Index: 1119676 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.7742. Min Act: -0.0000

Data Index: 270435 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.7480. Min Act: -0.0000

Data Index: 278811 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.7255. Min Act: -0.0000

Data Index: 541856 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.6151. Min Act: -0.0000

Data Index: 1030639 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.5839. Min Act: -0.0000

Data Index: 91697 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.5736. Min Act: -0.0000

Data Index: 1312495 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.4290. Min Act: -0.0000

Data Index: 152487 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.5507. Min Act: -0.0000

Data Index: 614567 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 5.8912. Min Range: -5.8912

Max Act: 3.5250. Min Act: -0.0000

Data Index: 388002 (C4 (Web Text))

Max Activating Token Index: 24