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

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

Neuron 2665 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4697. Min Range: -3.4697

Max Act: 3.0420. Min Act: -0.0001

Data Index: 1031027 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 3.4697. Min Range: -3.4697

Max Act: 3.1933. Min Act: -0.0001

Data Index: 599204 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.4697. Min Range: -3.4697

Max Act: 3.4697. Min Act: -0.0001

Data Index: 170965 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.4697. Min Range: -3.4697

Max Act: 3.2518. Min Act: -0.0001

Data Index: 935898 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.5345. Min Act: -0.0001

Data Index: 1180489 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.8553. Min Act: -0.0001

Data Index: 1225192 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.9171. Min Act: -0.0001

Data Index: 963183 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.9125. Min Act: -0.0001

Data Index: 498873 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 3.4697. Min Range: -3.4697

Max Act: 3.0512. Min Act: -0.0001

Data Index: 73344 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.8045. Min Act: -0.0001

Data Index: 1345755 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.8549. Min Act: -0.0001

Data Index: 811797 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.9128. Min Act: -0.0001

Data Index: 401521 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.8198. Min Act: -0.0001

Data Index: 139845 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.6324. Min Act: -0.0001

Data Index: 77431 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.5156. Min Act: -0.0001

Data Index: 393545 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.2534. Min Act: -0.0001

Data Index: 229741 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.4098. Min Act: -0.0001

Data Index: 204057 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.4933. Min Act: -0.0001

Data Index: 388359 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.5779. Min Act: -0.0001

Data Index: 574701 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 3.4697. Min Range: -3.4697

Max Act: 2.2360. Min Act: -0.0001

Data Index: 1046153 (C4 (Web Text))

Max Activating Token Index: 360