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

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

Neuron 3104 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1070261 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2157. Min Act: -0.0000

Data Index: 740030 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1409. Min Act: -0.0000

Data Index: 48662 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1241523 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1862. Min Act: -0.0000

Data Index: 643056 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1276535 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1032. Min Act: -0.0000

Data Index: 801046 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0602. Min Act: -0.0000

Data Index: 454737 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1097. Min Act: -0.0000

Data Index: 518026 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0218. Min Act: -0.0000

Data Index: 280276 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1083656 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1344416 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9283. Min Act: 0.0000

Data Index: 1285987 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1326497 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9093. Min Act: -0.0000

Data Index: 57158 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9595. Min Act: -0.0000

Data Index: 297121 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1108058 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9412. Min Act: -0.0000

Data Index: 456780 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9359. Min Act: -0.0000

Data Index: 614060 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9327. Min Act: -0.0000

Data Index: 333303 (C4 (Web Text))

Max Activating Token Index: 804