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

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

Neuron 3407 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: 0.0531. Min Range: -0.0531

Max Act: 0.0525. Min Act: -0.0002

Data Index: 731204 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0522. Min Act: -0.0002

Data Index: 314228 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0002

Data Index: 655725 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0508. Min Act: -0.0002

Data Index: 474556 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1393096 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1173615 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0442. Min Act: -0.0002

Data Index: 390532 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0457. Min Act: -0.0002

Data Index: 969162 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0441. Min Act: -0.0002

Data Index: 392102 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0430. Min Act: -0.0002

Data Index: 281591 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0413. Min Act: -0.0002

Data Index: 188218 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0429. Min Act: -0.0002

Data Index: 960564 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0427. Min Act: -0.0002

Data Index: 966008 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0426. Min Act: -0.0002

Data Index: 357348 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0401. Min Act: -0.0002

Data Index: 415696 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0406. Min Act: -0.0002

Data Index: 932919 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0397. Min Act: -0.0002

Data Index: 173069 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0400. Min Act: -0.0002

Data Index: 335130 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1435901 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1263083 (C4 (Web Text))

Max Activating Token Index: 645