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

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

Neuron 5561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0104. Min Range: -7.0104

Max Act: 7.0104. Min Act: -0.0001

Data Index: 675664 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.7841. Min Act: -0.0001

Data Index: 205714 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.6100. Min Act: -0.0001

Data Index: 898911 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.2383. Min Act: -0.0001

Data Index: 798365 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.2365. Min Act: -0.0001

Data Index: 402292 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.7153. Min Act: -0.0001

Data Index: 1087315 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.8035. Min Act: -0.0001

Data Index: 1018102 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.6437. Min Act: -0.0001

Data Index: 744681 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.7041. Min Act: -0.0001

Data Index: 1201756 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.9888. Min Act: -0.0001

Data Index: 675329 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.7980. Min Act: -0.0001

Data Index: 567830 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.7496. Min Act: -0.0001

Data Index: 34049 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.8750. Min Act: -0.0001

Data Index: 1290749 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.6329. Min Act: -0.0001

Data Index: 1192742 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.5973. Min Act: -0.0001

Data Index: 547321 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 7.0104. Min Range: -7.0104

Max Act: 6.0580. Min Act: -0.0001

Data Index: 1170927 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.4511. Min Act: -0.0001

Data Index: 498496 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.6295. Min Act: -0.0001

Data Index: 920430 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.4368. Min Act: -0.0001

Data Index: 175764 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 7.0104. Min Range: -7.0104

Max Act: 5.2229. Min Act: -0.0001

Data Index: 736921 (C4 (Web Text))

Max Activating Token Index: 409