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

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

Neuron 3692 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.9294. Min Act: -0.0000

Data Index: 1208946 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.9328. Min Act: -0.0000

Data Index: 725294 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 2.1628. Min Range: -2.1628

Max Act: 2.1628. Min Act: -0.0000

Data Index: 613647 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.9705. Min Act: -0.0000

Data Index: 852013 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.7240. Min Act: -0.0000

Data Index: 156671 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.6258. Min Act: -0.0000

Data Index: 102431 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.7050. Min Act: -0.0000

Data Index: 185521 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.6205. Min Act: -0.0000

Data Index: 443897 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.4906. Min Act: -0.0000

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.1517. Min Act: -0.0000

Data Index: 429274 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1007654 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.4992. Min Act: -0.0000

Data Index: 500813 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.3418. Min Act: -0.0000

Data Index: 617544 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1059236 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.4042. Min Act: -0.0000

Data Index: 669244 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1014956 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.6039. Min Act: -0.0000

Data Index: 136282 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.4760. Min Act: -0.0000

Data Index: 372332 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.2639. Min Act: -0.0000

Data Index: 741141 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 2.1628. Min Range: -2.1628

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1339539 (C4 (Web Text))

Max Activating Token Index: 513