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

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

Neuron 2590 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: 1.0945. Min Range: -1.0945

Max Act: 1.0945. Min Act: -0.0001

Data Index: 951040 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 1.0945. Min Range: -1.0945

Max Act: 1.0316. Min Act: -0.0001

Data Index: 871996 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.9143. Min Act: -0.0001

Data Index: 16695 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.9683. Min Act: -0.0001

Data Index: 1029909 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8911. Min Act: -0.0000

Data Index: 11399 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.9073. Min Act: -0.0000

Data Index: 382915 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8600. Min Act: -0.0001

Data Index: 749164 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8755. Min Act: -0.0000

Data Index: 728706 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8629. Min Act: -0.0000

Data Index: 491507 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.7931. Min Act: -0.0000

Data Index: 654930 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8588. Min Act: -0.0001

Data Index: 591968 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1163454 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.7962. Min Act: -0.0001

Data Index: 367792 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.6347. Min Act: -0.0000

Data Index: 418093 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8020. Min Act: -0.0001

Data Index: 685291 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.7266. Min Act: -0.0001

Data Index: 812284 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8122. Min Act: -0.0001

Data Index: 640780 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.7780. Min Act: -0.0000

Data Index: 384615 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1036455 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 1.0945. Min Range: -1.0945

Max Act: 0.8530. Min Act: -0.0001

Data Index: 1019902 (C4 (Web Text))

Max Activating Token Index: 825