Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2382 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.5446. Min Act: -0.0000

Data Index: 55660 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.8530. Min Act: -0.0000

Data Index: 679216 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 4.8530. Min Range: -4.8530

Max Act: 4.5177. Min Act: -0.0000

Data Index: 1149583 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.8933. Min Act: -0.0001

Data Index: 848766 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.7099. Min Act: -0.0001

Data Index: 422529 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.5253. Min Act: -0.0000

Data Index: 716573 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.3532. Min Act: -0.0000

Data Index: 1352973 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.1877. Min Act: -0.0000

Data Index: 648643 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.2138. Min Act: -0.0000

Data Index: 1017545 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.1377. Min Act: -0.0000

Data Index: 236647 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.1414. Min Act: -0.0000

Data Index: 201285 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.8287. Min Act: -0.0000

Data Index: 140489 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.0045. Min Act: -0.0000

Data Index: 931638 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.9454. Min Act: -0.0001

Data Index: 735660 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.9489. Min Act: -0.0000

Data Index: 673490 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 4.8530. Min Range: -4.8530

Max Act: 3.0680. Min Act: -0.0000

Data Index: 692778 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.8826. Min Act: -0.0000

Data Index: 1339433 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.8064. Min Act: -0.0000

Data Index: 442148 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.5359. Min Act: -0.0000

Data Index: 507463 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 4.8530. Min Range: -4.8530

Max Act: 2.8882. Min Act: -0.0001

Data Index: 670626 (C4 (Web Text))

Max Activating Token Index: 799