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

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

Neuron 1165 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: 3.1278. Min Range: -3.1278

Max Act: 3.1278. Min Act: -0.0000

Data Index: 1218808 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.9012. Min Act: -0.0000

Data Index: 690019 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.8077. Min Act: -0.0000

Data Index: 13849 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.7954. Min Act: -0.0000

Data Index: 46295 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.7824. Min Act: -0.0000

Data Index: 845496 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.7520. Min Act: -0.0000

Data Index: 812251 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.7134. Min Act: -0.0000

Data Index: 153122 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.5594. Min Act: -0.0000

Data Index: 795068 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.5148. Min Act: -0.0000

Data Index: 198332 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.6842. Min Act: -0.0000

Data Index: 1104572 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.4284. Min Act: -0.0000

Data Index: 249408 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.5472. Min Act: -0.0000

Data Index: 332305 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.5228. Min Act: -0.0000

Data Index: 452239 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.4665. Min Act: -0.0000

Data Index: 567206 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.4804. Min Act: -0.0000

Data Index: 896912 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.4459. Min Act: -0.0000

Data Index: 408261 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.4185. Min Act: -0.0000

Data Index: 184941 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.6828. Min Act: -0.0000

Data Index: 46515 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.2804. Min Act: -0.0000

Data Index: 519492 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.1278. Min Range: -3.1278

Max Act: 2.2666. Min Act: -0.0000

Data Index: 892729 (C4 (Web Text))

Max Activating Token Index: 282