Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 930 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.5019. Min Range: -5.5019

Max Act: 5.5019. Min Act: -0.0000

Data Index: 1561014 (Python Code)

Max Activating Token Index: 519

Text #1

Max Range: 5.5019. Min Range: -5.5019

Max Act: 5.2149. Min Act: -0.0000

Data Index: 1039649 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.9595. Min Act: -0.0000

Data Index: 644142 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 5.5019. Min Range: -5.5019

Max Act: 5.1115. Min Act: -0.0000

Data Index: 1202401 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.6601. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.6179. Min Act: -0.0000

Data Index: 1407976 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.5169. Min Act: -0.0000

Data Index: 376218 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.8406. Min Act: -0.0000

Data Index: 94727 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.6300. Min Act: -0.0000

Data Index: 1638620 (Python Code)

Max Activating Token Index: 783

Text #9

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.7462. Min Act: -0.0000

Data Index: 1544584 (Python Code)

Max Activating Token Index: 779

Text #10

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.4396. Min Act: -0.0000

Data Index: 44342 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.2746. Min Act: -0.0000

Data Index: 1654519 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.0968. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.2056. Min Act: -0.0000

Data Index: 495914 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.0455. Min Act: -0.0000

Data Index: 757353 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.3067. Min Act: -0.0000

Data Index: 1355636 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 5.5019. Min Range: -5.5019

Max Act: 4.1210. Min Act: -0.0000

Data Index: 1462279 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 5.5019. Min Range: -5.5019

Max Act: 3.9339. Min Act: -0.0000

Data Index: 922954 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 5.5019. Min Range: -5.5019

Max Act: 3.8647. Min Act: -0.0000

Data Index: 545461 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 5.5019. Min Range: -5.5019

Max Act: 3.8136. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 501