Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2665 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.9555. Min Act: -0.0000

Data Index: 140647 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.8553. Min Act: -0.0000

Data Index: 817333 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.8277. Min Act: -0.0000

Data Index: 141321 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1123486 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7949. Min Act: -0.0000

Data Index: 664826 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7713. Min Act: -0.0000

Data Index: 504041 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1359603 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7477. Min Act: -0.0000

Data Index: 559668 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6666. Min Act: 0.0000

Data Index: 1616307 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7292. Min Act: -0.0000

Data Index: 886492 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7140. Min Act: -0.0000

Data Index: 333453 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1348082 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7225. Min Act: -0.0000

Data Index: 168339 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1358103 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6868. Min Act: -0.0000

Data Index: 384108 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7155. Min Act: -0.0000

Data Index: 193368 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1327806 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7121. Min Act: -0.0000

Data Index: 238840 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6481. Min Act: -0.0000

Data Index: 413181 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6314. Min Act: 0.0001

Data Index: 1380614 (Python Code)

Max Activating Token Index: 68