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

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

Neuron 1973 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.5343. Min Act: 0.0000

Data Index: 724373 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4913. Min Act: -0.0000

Data Index: 658407 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4865. Min Act: -0.0000

Data Index: 161196 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4824. Min Act: -0.0000

Data Index: 325408 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4602. Min Act: -0.0000

Data Index: 622738 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4355. Min Act: -0.0000

Data Index: 483423 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4537. Min Act: -0.0000

Data Index: 645745 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4514. Min Act: -0.0000

Data Index: 429222 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4472. Min Act: -0.0000

Data Index: 656927 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4467. Min Act: -0.0000

Data Index: 721252 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4390. Min Act: -0.0000

Data Index: 197748 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4296. Min Act: -0.0000

Data Index: 24834 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1274387 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1259881 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4323. Min Act: -0.0000

Data Index: 870681 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4285. Min Act: -0.0000

Data Index: 688014 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1202908 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1269853 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4401. Min Act: -0.0000

Data Index: 995599 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4165. Min Act: -0.0000

Data Index: 969593 (C4 (Web Text))

Max Activating Token Index: 506