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

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

Neuron 4701 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: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0002

Data Index: 250015 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1080711 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1339878 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0503. Min Act: -0.0002

Data Index: 66758 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0531. Min Act: -0.0002

Data Index: 889885 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1214851 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0500. Min Act: -0.0002

Data Index: 638824 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1163943 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0484. Min Act: -0.0002

Data Index: 2333 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0460. Min Act: -0.0002

Data Index: 705374 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0481. Min Act: -0.0002

Data Index: 686876 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0500. Min Act: -0.0002

Data Index: 190330 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1126544 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0476. Min Act: -0.0002

Data Index: 21221 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0471. Min Act: -0.0002

Data Index: 54758 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0490. Min Act: -0.0002

Data Index: 502689 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1292916 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0467. Min Act: -0.0002

Data Index: 892733 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0481. Min Act: -0.0002

Data Index: 160714 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0444. Min Act: -0.0002

Data Index: 504275 (C4 (Web Text))

Max Activating Token Index: 202