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

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

Neuron 468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.6178. Min Act: -0.0002

Data Index: 594365 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.6026. Min Act: -0.0002

Data Index: 61766 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5657. Min Act: -0.0002

Data Index: 759513 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5182. Min Act: -0.0002

Data Index: 672610 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5500. Min Act: -0.0002

Data Index: 164587 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5268. Min Act: -0.0002

Data Index: 1215571 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5525. Min Act: -0.0002

Data Index: 962402 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5629. Min Act: -0.0002

Data Index: 863449 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.5393. Min Act: -0.0002

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4944. Min Act: -0.0002

Data Index: 576679 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4770. Min Act: -0.0002

Data Index: 224203 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4932. Min Act: -0.0002

Data Index: 1151100 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4872. Min Act: -0.0002

Data Index: 640527 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4864. Min Act: -0.0002

Data Index: 1291056 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4577. Min Act: -0.0002

Data Index: 705145 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4847. Min Act: -0.0002

Data Index: 930496 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4622. Min Act: -0.0002

Data Index: 1281338 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4323. Min Act: -0.0002

Data Index: 498201 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4601. Min Act: -0.0002

Data Index: 278357 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.6178. Min Range: -0.6178

Max Act: 0.4595. Min Act: -0.0002

Data Index: 110840 (C4 (Web Text))

Max Activating Token Index: 535