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

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

Neuron 4444 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: 1.1765. Min Range: -1.1765

Max Act: 1.1431. Min Act: -0.0000

Data Index: 838933 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.1765. Min Act: -0.0000

Data Index: 317240 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.0912. Min Act: -0.0000

Data Index: 121959 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1104670 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1343284 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9789. Min Act: 0.0000

Data Index: 597693 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9967. Min Act: -0.0000

Data Index: 836346 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.1765. Min Range: -1.1765

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1070428 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9339. Min Act: 0.0000

Data Index: 623768 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9512. Min Act: -0.0000

Data Index: 10801 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8770. Min Act: 0.0000

Data Index: 477179 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9316. Min Act: -0.0000

Data Index: 344766 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9296. Min Act: -0.0000

Data Index: 713044 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9222. Min Act: 0.0000

Data Index: 1015352 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9320. Min Act: -0.0000

Data Index: 67776 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.9456. Min Act: -0.0000

Data Index: 629323 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8640. Min Act: -0.0000

Data Index: 693646 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8719. Min Act: 0.0000

Data Index: 602121 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8351. Min Act: -0.0000

Data Index: 882128 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.1765. Min Range: -1.1765

Max Act: 0.8625. Min Act: -0.0000

Data Index: 923011 (C4 (Web Text))

Max Activating Token Index: 781