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

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

Neuron 1328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5537. Min Range: -4.5537

Max Act: 4.5537. Min Act: -0.0000

Data Index: 1504937 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.9833. Min Act: -0.0000

Data Index: 369991 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 4.5537. Min Range: -4.5537

Max Act: 4.2404. Min Act: -0.0000

Data Index: 729973 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.9441. Min Act: -0.0000

Data Index: 630698 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.9514. Min Act: -0.0000

Data Index: 876208 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.8158. Min Act: -0.0000

Data Index: 977488 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.8012. Min Act: -0.0000

Data Index: 44416 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.7778. Min Act: -0.0000

Data Index: 593153 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5819. Min Act: -0.0000

Data Index: 165885 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.7564. Min Act: -0.0000

Data Index: 1290642 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5757. Min Act: -0.0000

Data Index: 195206 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.7921. Min Act: -0.0000

Data Index: 1226440 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.6088. Min Act: -0.0000

Data Index: 907315 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.6189. Min Act: -0.0000

Data Index: 560971 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5487. Min Act: -0.0000

Data Index: 880979 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5105. Min Act: -0.0000

Data Index: 323262 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5120. Min Act: -0.0000

Data Index: 751676 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.3090. Min Act: -0.0000

Data Index: 178403 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.4579. Min Act: -0.0000

Data Index: 404875 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.4134. Min Act: -0.0000

Data Index: 1183148 (C4 (Web Text))

Max Activating Token Index: 14