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

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

Neuron 526 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: 1.4612. Min Range: -1.4612

Max Act: 1.4612. Min Act: -0.0001

Data Index: 1310218 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.3264. Min Act: -0.0001

Data Index: 1319822 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2952. Min Act: -0.0002

Data Index: 83992 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1485. Min Act: -0.0001

Data Index: 1124263 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2167. Min Act: -0.0002

Data Index: 1299820 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2091. Min Act: -0.0002

Data Index: 262483 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.2076. Min Act: -0.0001

Data Index: 333332 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1662. Min Act: -0.0002

Data Index: 1279523 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1697. Min Act: -0.0001

Data Index: 1039381 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1311. Min Act: -0.0001

Data Index: 541580 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1416. Min Act: -0.0001

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1428. Min Act: -0.0001

Data Index: 884163 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.1112. Min Act: -0.0002

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.0249. Min Act: -0.0001

Data Index: 262041 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.0230. Min Act: -0.0002

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.0574. Min Act: -0.0002

Data Index: 498693 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.0364. Min Act: -0.0002

Data Index: 556335 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.4612. Min Range: -1.4612

Max Act: 1.0121. Min Act: -0.0001

Data Index: 739721 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9734. Min Act: -0.0001

Data Index: 1127864 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.4612. Min Range: -1.4612

Max Act: 0.9364. Min Act: -0.0002

Data Index: 1280631 (C4 (Web Text))

Max Activating Token Index: 242