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

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

Neuron 4004 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: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 203416 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3454. Min Act: -0.0000

Data Index: 1032304 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2136. Min Act: -0.0000

Data Index: 625031 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1022733 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0817. Min Act: -0.0000

Data Index: 382846 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1171. Min Act: -0.0000

Data Index: 202857 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1018. Min Act: -0.0000

Data Index: 209762 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0539. Min Act: -0.0000

Data Index: 507881 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0749. Min Act: -0.0000

Data Index: 653655 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1277. Min Act: -0.0000

Data Index: 561044 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1139735 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1200. Min Act: -0.0000

Data Index: 572400 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0434. Min Act: -0.0000

Data Index: 77103 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0156. Min Act: -0.0000

Data Index: 726492 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0327. Min Act: -0.0000

Data Index: 236368 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9799. Min Act: -0.0000

Data Index: 844298 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0008. Min Act: -0.0000

Data Index: 556252 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1066785 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1191141 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1159334 (C4 (Web Text))

Max Activating Token Index: 782