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

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

Neuron 514 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: 1.4574. Min Range: -1.4574

Max Act: 1.4574. Min Act: -0.0000

Data Index: 507930 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 1.4574. Min Range: -1.4574

Max Act: 1.0455. Min Act: -0.0000

Data Index: 247471 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.7866. Min Act: -0.0000

Data Index: 701501 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.8222. Min Act: -0.0000

Data Index: 967632 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.6729. Min Act: -0.0000

Data Index: 139685 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.8137. Min Act: -0.0000

Data Index: 722421 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.5368. Min Act: -0.0000

Data Index: 740474 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.5068. Min Act: -0.0000

Data Index: 384040 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.5991. Min Act: -0.0000

Data Index: 517779 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.6175. Min Act: -0.0000

Data Index: 53834 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.5804. Min Act: -0.0000

Data Index: 469676 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1238669 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1212721 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.4819. Min Act: -0.0000

Data Index: 896478 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1199930 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.3884. Min Act: -0.0000

Data Index: 903358 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.5030. Min Act: -0.0000

Data Index: 725729 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.4600. Min Act: -0.0000

Data Index: 66902 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.4432. Min Act: -0.0000

Data Index: 819290 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.4574. Min Range: -1.4574

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1065511 (C4 (Web Text))

Max Activating Token Index: 250