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

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

Neuron 984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.6652. Min Act: -0.0000

Data Index: 341223 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.6311. Min Act: -0.0001

Data Index: 413260 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5979. Min Act: -0.0000

Data Index: 991783 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5850. Min Act: -0.0000

Data Index: 151895 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5570. Min Act: -0.0000

Data Index: 176298 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5040. Min Act: -0.0000

Data Index: 188927 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5025. Min Act: -0.0000

Data Index: 861388 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5108. Min Act: -0.0000

Data Index: 589899 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5191. Min Act: 0.0000

Data Index: 758701 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4934. Min Act: -0.0000

Data Index: 115187 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1338572 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4870. Min Act: 0.0000

Data Index: 41574 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.5005. Min Act: 0.0000

Data Index: 307505 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4959. Min Act: -0.0000

Data Index: 454697 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4907. Min Act: -0.0000

Data Index: 705646 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4528. Min Act: -0.0000

Data Index: 25695 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4591. Min Act: -0.0000

Data Index: 472908 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4681. Min Act: -0.0001

Data Index: 265511 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4522. Min Act: -0.0001

Data Index: 670251 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.6652. Min Range: -0.6652

Max Act: 0.4340. Min Act: 0.0000

Data Index: 502338 (C4 (Web Text))

Max Activating Token Index: 76