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

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

Neuron 2499 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5203. Min Act: -0.0001

Data Index: 1007448 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4204. Min Act: -0.0000

Data Index: 82080 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4668. Min Act: 0.0000

Data Index: 1178845 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4655. Min Act: -0.0001

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4521. Min Act: -0.0000

Data Index: 316378 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4237. Min Act: -0.0000

Data Index: 187222 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1228933 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3640. Min Act: -0.0000

Data Index: 595162 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1056039 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3628. Min Act: -0.0000

Data Index: 143983 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3408. Min Act: -0.0001

Data Index: 1333778 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1223142 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3571. Min Act: -0.0000

Data Index: 100322 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3430. Min Act: -0.0000

Data Index: 574792 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3406. Min Act: -0.0000

Data Index: 546017 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1136650 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1350035 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3185. Min Act: -0.0000

Data Index: 936897 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3163. Min Act: -0.0001

Data Index: 353729 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3262. Min Act: -0.0000

Data Index: 846553 (C4 (Web Text))

Max Activating Token Index: 387