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

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

Neuron 3105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1770. Min Range: -5.1770

Max Act: 5.1770. Min Act: -0.0000

Data Index: 922621 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.7678. Min Act: -0.0000

Data Index: 986588 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.3718. Min Act: -0.0000

Data Index: 4079 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.4177. Min Act: -0.0000

Data Index: 945080 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.3709. Min Act: -0.0000

Data Index: 380104 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.1859. Min Act: -0.0000

Data Index: 1072373 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.1243. Min Act: -0.0000

Data Index: 224523 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.8459. Min Act: -0.0000

Data Index: 1325572 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 5.1770. Min Range: -5.1770

Max Act: 4.0803. Min Act: -0.0000

Data Index: 903949 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.7309. Min Act: -0.0000

Data Index: 932417 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.8785. Min Act: -0.0000

Data Index: 656835 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.8215. Min Act: -0.0000

Data Index: 896635 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.6448. Min Act: -0.0000

Data Index: 358063 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.6442. Min Act: -0.0000

Data Index: 451211 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.6146. Min Act: -0.0000

Data Index: 958635 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.7731. Min Act: -0.0000

Data Index: 333901 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.7382. Min Act: -0.0000

Data Index: 1214212 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.7392. Min Act: -0.0000

Data Index: 983945 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.4207. Min Act: -0.0000

Data Index: 597906 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 5.1770. Min Range: -5.1770

Max Act: 3.7158. Min Act: -0.0000

Data Index: 1062847 (C4 (Web Text))

Max Activating Token Index: 76