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

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

Neuron 19 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4296. Min Act: -0.0001

Data Index: 1019388 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4607. Min Act: -0.0001

Data Index: 1215151 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3024. Min Act: -0.0001

Data Index: 825594 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.0241. Min Act: -0.0001

Data Index: 1100345 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.1766. Min Act: -0.0000

Data Index: 1002260 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.1869. Min Act: -0.0001

Data Index: 389453 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.9072. Min Act: -0.0000

Data Index: 637195 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.8764. Min Act: -0.0000

Data Index: 97108 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.0373. Min Act: -0.0000

Data Index: 701255 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.8845. Min Act: -0.0001

Data Index: 670892 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.9477. Min Act: -0.0001

Data Index: 1271503 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.9791. Min Act: -0.0000

Data Index: 737816 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.6924. Min Act: -0.0001

Data Index: 310989 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.9522. Min Act: -0.0000

Data Index: 453043 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.8396. Min Act: -0.0000

Data Index: 726083 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.9411. Min Act: -0.0001

Data Index: 681774 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.7830. Min Act: -0.0000

Data Index: 994373 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.7256. Min Act: -0.0001

Data Index: 669541 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.8248. Min Act: -0.0001

Data Index: 758625 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 2.4607. Min Range: -2.4607

Max Act: 1.6961. Min Act: -0.0000

Data Index: 547553 (C4 (Web Text))

Max Activating Token Index: 988