Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3293 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6639. Min Act: -0.0001

Data Index: 259486 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1017193 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5475. Min Act: -0.0001

Data Index: 1030719 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5874. Min Act: -0.0001

Data Index: 1021679 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5164. Min Act: -0.0001

Data Index: 559954 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5523. Min Act: -0.0001

Data Index: 1012646 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5341. Min Act: -0.0001

Data Index: 605564 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5002. Min Act: -0.0001

Data Index: 534226 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.5372. Min Act: -0.0001

Data Index: 418202 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4869. Min Act: -0.0001

Data Index: 871945 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1196176 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4873. Min Act: -0.0001

Data Index: 345744 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4695. Min Act: -0.0001

Data Index: 797871 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4695. Min Act: -0.0000

Data Index: 998350 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4570. Min Act: -0.0001

Data Index: 341010 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4822. Min Act: -0.0001

Data Index: 169632 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4466. Min Act: -0.0001

Data Index: 437500 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4577. Min Act: -0.0001

Data Index: 481330 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4356. Min Act: -0.0000

Data Index: 880972 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.6639. Min Range: -0.6639

Max Act: 0.4635. Min Act: -0.0001

Data Index: 1158761 (C4 (Web Text))

Max Activating Token Index: 921