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

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

Neuron 5794 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5950. Min Act: -0.0000

Data Index: 303733 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5181. Min Act: -0.0000

Data Index: 65245 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1260455 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4743. Min Act: -0.0000

Data Index: 594224 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4439. Min Act: -0.0000

Data Index: 460867 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4595. Min Act: -0.0000

Data Index: 570902 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4472. Min Act: -0.0000

Data Index: 231462 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4362. Min Act: -0.0000

Data Index: 133391 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4584. Min Act: -0.0000

Data Index: 330861 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1122638 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4285. Min Act: -0.0000

Data Index: 148448 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4470. Min Act: -0.0000

Data Index: 873221 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4256. Min Act: -0.0000

Data Index: 520458 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1015063 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4541. Min Act: -0.0000

Data Index: 280758 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3943. Min Act: -0.0000

Data Index: 350577 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4345. Min Act: -0.0000

Data Index: 486102 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4404. Min Act: -0.0000

Data Index: 645577 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4246. Min Act: -0.0000

Data Index: 921745 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4094. Min Act: -0.0000

Data Index: 748807 (C4 (Web Text))

Max Activating Token Index: 920