Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.3595. Min Act: -0.0001

Data Index: 323186 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2392. Min Act: -0.0001

Data Index: 285800 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.3351. Min Act: -0.0001

Data Index: 614268 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1955. Min Act: -0.0001

Data Index: 578765 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1898. Min Act: -0.0001

Data Index: 481669 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2562. Min Act: -0.0001

Data Index: 779375 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2150. Min Act: -0.0001

Data Index: 1261921 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.3595. Min Range: -1.3595

Max Act: 0.9318. Min Act: -0.0001

Data Index: 1015216 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1048. Min Act: -0.0001

Data Index: 910929 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.2058. Min Act: -0.0001

Data Index: 398020 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0576. Min Act: -0.0001

Data Index: 764049 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0459. Min Act: -0.0001

Data Index: 100094 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1367. Min Act: -0.0001

Data Index: 489066 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1680. Min Act: -0.0001

Data Index: 1014144 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1526. Min Act: -0.0001

Data Index: 89469 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1300. Min Act: -0.0001

Data Index: 943751 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0964. Min Act: -0.0001

Data Index: 868718 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.1010. Min Act: -0.0001

Data Index: 587926 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0838. Min Act: -0.0001

Data Index: 1331204 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.3595. Min Range: -1.3595

Max Act: 1.0473. Min Act: -0.0001

Data Index: 334367 (C4 (Web Text))

Max Activating Token Index: 296