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

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

Neuron 2986 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: 1.1899. Min Range: -1.1899

Max Act: 1.1899. Min Act: -0.0001

Data Index: 582549 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0470. Min Act: -0.0001

Data Index: 104337 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0293. Min Act: -0.0001

Data Index: 546363 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.1642. Min Act: -0.0001

Data Index: 743283 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0500. Min Act: -0.0001

Data Index: 1203266 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0255. Min Act: -0.0001

Data Index: 501179 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9200. Min Act: -0.0001

Data Index: 1315785 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1315574 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9432. Min Act: -0.0001

Data Index: 341376 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.1899. Min Range: -1.1899

Max Act: 1.0434. Min Act: -0.0001

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9465. Min Act: -0.0001

Data Index: 945827 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9265. Min Act: -0.0001

Data Index: 1317637 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.8079. Min Act: -0.0001

Data Index: 595109 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9159. Min Act: -0.0001

Data Index: 788 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.8529. Min Act: -0.0001

Data Index: 409316 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1312498 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.8782. Min Act: -0.0001

Data Index: 1228732 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.9669. Min Act: -0.0001

Data Index: 864128 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.8663. Min Act: -0.0001

Data Index: 225495 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 1.1899. Min Range: -1.1899

Max Act: 0.8949. Min Act: -0.0001

Data Index: 861397 (C4 (Web Text))

Max Activating Token Index: 797