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

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

Neuron 1242 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0001

Data Index: 31999 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0649. Min Act: -0.0001

Data Index: 427085 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0514. Min Act: -0.0001

Data Index: 467020 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0494. Min Act: -0.0001

Data Index: 162273 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1039272 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0440. Min Act: -0.0001

Data Index: 137513 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1264015 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1266372 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0426. Min Act: -0.0001

Data Index: 962670 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0421. Min Act: -0.0001

Data Index: 260646 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1076472 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1140700 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0388. Min Act: -0.0001

Data Index: 312485 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1201260 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0406. Min Act: -0.0001

Data Index: 220931 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1057297 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1154150 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1206059 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1266117 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0372. Min Act: -0.0001

Data Index: 649111 (C4 (Web Text))

Max Activating Token Index: 701