Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2398. Min Range: -3.2398

Max Act: 3.0434. Min Act: -0.0001

Data Index: 549337 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.2398. Min Range: -3.2398

Max Act: 3.2398. Min Act: -0.0001

Data Index: 1182811 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.8356. Min Act: -0.0001

Data Index: 1064093 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.7792. Min Act: -0.0001

Data Index: 789474 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.7529. Min Act: -0.0001

Data Index: 1312373 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.8502. Min Act: -0.0001

Data Index: 919013 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.6719. Min Act: -0.0001

Data Index: 858045 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 3.2398. Min Range: -3.2398

Max Act: 3.0102. Min Act: -0.0001

Data Index: 185982 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.7366. Min Act: -0.0001

Data Index: 152400 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.7324. Min Act: -0.0001

Data Index: 1254423 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.7246. Min Act: -0.0001

Data Index: 680883 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.5884. Min Act: -0.0001

Data Index: 56177 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.6842. Min Act: -0.0001

Data Index: 1058099 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.9296. Min Act: -0.0001

Data Index: 735770 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.6898. Min Act: -0.0001

Data Index: 664357 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.3782. Min Act: -0.0001

Data Index: 1350989 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.2598. Min Act: -0.0001

Data Index: 889091 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.6082. Min Act: -0.0001

Data Index: 1018323 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.4371. Min Act: -0.0001

Data Index: 332360 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 3.2398. Min Range: -3.2398

Max Act: 2.4371. Min Act: -0.0001

Data Index: 1265684 (C4 (Web Text))

Max Activating Token Index: 3