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

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

Neuron 1182 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: 1.3815. Min Range: -1.3815

Max Act: 1.3815. Min Act: -0.0001

Data Index: 1359615 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.3815. Min Range: -1.3815

Max Act: 1.1258. Min Act: -0.0001

Data Index: 318088 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8740. Min Act: -0.0001

Data Index: 704894 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7776. Min Act: -0.0001

Data Index: 786177 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1016086 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8792. Min Act: -0.0001

Data Index: 281657 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8203. Min Act: -0.0001

Data Index: 340388 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8163. Min Act: -0.0001

Data Index: 1134210 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7793. Min Act: -0.0001

Data Index: 719682 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.8316. Min Act: -0.0001

Data Index: 42181 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7584. Min Act: -0.0001

Data Index: 744983 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7288. Min Act: -0.0001

Data Index: 975885 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7461. Min Act: -0.0001

Data Index: 445586 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7337. Min Act: -0.0001

Data Index: 968032 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1212487 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7260. Min Act: -0.0001

Data Index: 572401 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.7898. Min Act: -0.0001

Data Index: 985156 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.6954. Min Act: -0.0001

Data Index: 977566 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.6701. Min Act: -0.0001

Data Index: 1214670 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 1.3815. Min Range: -1.3815

Max Act: 0.6678. Min Act: -0.0001

Data Index: 119813 (C4 (Web Text))

Max Activating Token Index: 719