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

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

Neuron 9 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.1271. Min Act: -0.0000

Data Index: 240239 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0527. Min Act: 0.0001

Data Index: 715523 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0445. Min Act: 0.0001

Data Index: 448746 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9159. Min Act: 0.0001

Data Index: 169134 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8640. Min Act: 0.0001

Data Index: 268382 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8151. Min Act: 0.0000

Data Index: 45381 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8082. Min Act: 0.0000

Data Index: 1217162 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1499762 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7979. Min Act: 0.0000

Data Index: 723468 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8235. Min Act: -0.0000

Data Index: 586355 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7908. Min Act: -0.0000

Data Index: 181684 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7745. Min Act: -0.0000

Data Index: 80276 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7457. Min Act: -0.0000

Data Index: 44845 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1560989 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1395045 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7836. Min Act: 0.0000

Data Index: 924198 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1635980 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1551788 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7499. Min Act: -0.0000

Data Index: 212965 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1548305 (Python Code)

Max Activating Token Index: 430