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

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

Neuron 3 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7586. Min Act: -0.0001

Data Index: 756749 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8052. Min Act: -0.0002

Data Index: 233600 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1215770 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7465. Min Act: -0.0001

Data Index: 404407 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1138028 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6684. Min Act: -0.0002

Data Index: 1086178 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6310. Min Act: -0.0002

Data Index: 1059638 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6719. Min Act: -0.0001

Data Index: 755065 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6616. Min Act: -0.0002

Data Index: 1081887 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6504. Min Act: -0.0002

Data Index: 838346 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6250. Min Act: -0.0002

Data Index: 730836 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6330. Min Act: -0.0002

Data Index: 625414 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6022. Min Act: -0.0002

Data Index: 882163 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6325. Min Act: -0.0001

Data Index: 371601 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6091. Min Act: -0.0002

Data Index: 852740 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6354. Min Act: -0.0002

Data Index: 1181812 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6433. Min Act: -0.0002

Data Index: 292880 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.6590. Min Act: -0.0002

Data Index: 420817 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.7106. Min Act: -0.0002

Data Index: 616271 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.8538. Min Range: -0.8538

Max Act: 0.5980. Min Act: -0.0001

Data Index: 139219 (C4 (Web Text))

Max Activating Token Index: 465