Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2676 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1457. Min Range: -1.1457

Max Act: 1.1457. Min Act: -0.0000

Data Index: 391362 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.1457. Min Range: -1.1457

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1196880 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.1457. Min Range: -1.1457

Max Act: 1.0554. Min Act: -0.0000

Data Index: 153833 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.1457. Min Range: -1.1457

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1085912 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1161136 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9326. Min Act: -0.0000

Data Index: 937606 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9035. Min Act: -0.0000

Data Index: 495657 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9753. Min Act: -0.0000

Data Index: 801611 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9389. Min Act: 0.0001

Data Index: 545618 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9227. Min Act: -0.0000

Data Index: 898768 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.9179. Min Act: -0.0000

Data Index: 122208 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1273627 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8743. Min Act: 0.0000

Data Index: 1111936 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1290753 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8718. Min Act: -0.0000

Data Index: 416372 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8681. Min Act: -0.0000

Data Index: 689327 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8678. Min Act: -0.0000

Data Index: 566877 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8688. Min Act: -0.0000

Data Index: 20978 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8875. Min Act: -0.0000

Data Index: 122593 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 1.1457. Min Range: -1.1457

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1134705 (C4 (Web Text))

Max Activating Token Index: 712