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

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

Neuron 1562 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.1268. Min Act: -0.0001

Data Index: 808318 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.1497. Min Act: -0.0002

Data Index: 454997 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.0163. Min Act: -0.0001

Data Index: 1174077 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.0765. Min Act: -0.0001

Data Index: 134568 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.0669. Min Act: -0.0002

Data Index: 1143705 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.0308. Min Act: -0.0002

Data Index: 1325698 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.0515. Min Act: -0.0002

Data Index: 909336 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8610. Min Act: -0.0002

Data Index: 646689 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9559. Min Act: -0.0001

Data Index: 1238025 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9988. Min Act: -0.0002

Data Index: 922509 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9047. Min Act: -0.0002

Data Index: 423474 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9101. Min Act: -0.0002

Data Index: 1200145 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8725. Min Act: -0.0001

Data Index: 292271 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9258. Min Act: -0.0002

Data Index: 430124 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9024. Min Act: -0.0002

Data Index: 327897 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9356. Min Act: -0.0002

Data Index: 211471 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9097. Min Act: -0.0002

Data Index: 400599 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8576. Min Act: -0.0001

Data Index: 818469 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8670. Min Act: -0.0002

Data Index: 222289 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8983. Min Act: -0.0002

Data Index: 1021609 (C4 (Web Text))

Max Activating Token Index: 18