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

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

Neuron 3965 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.8947. Min Act: -0.0000

Data Index: 1340670 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.5587. Min Act: -0.0000

Data Index: 554175 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.4766. Min Act: -0.0000

Data Index: 309869 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.3302. Min Act: -0.0000

Data Index: 138317 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.3736. Min Act: -0.0000

Data Index: 332178 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2745. Min Act: -0.0000

Data Index: 415032 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2356. Min Act: -0.0000

Data Index: 206413 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.2323. Min Act: -0.0000

Data Index: 90710 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1875. Min Act: -0.0000

Data Index: 383709 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1179536 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1162. Min Act: -0.0000

Data Index: 99756 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1428. Min Act: -0.0000

Data Index: 375403 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1568. Min Act: -0.0000

Data Index: 351132 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1679. Min Act: -0.0000

Data Index: 879952 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.0504. Min Act: -0.0000

Data Index: 107050 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1171. Min Act: -0.0000

Data Index: 867305 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1567. Min Act: -0.0000

Data Index: 572718 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.1467. Min Act: -0.0000

Data Index: 673890 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1105602 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.8947. Min Range: -1.8947

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1076659 (C4 (Web Text))

Max Activating Token Index: 981