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

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

Neuron 2394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5804. Min Range: -3.5804

Max Act: 3.5804. Min Act: -0.0001

Data Index: 1136182 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.7695. Min Act: -0.0001

Data Index: 1638692 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.7520. Min Act: -0.0001

Data Index: 844234 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.5995. Min Act: -0.0001

Data Index: 1201899 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.4124. Min Act: -0.0001

Data Index: 1257569 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.1151. Min Act: -0.0001

Data Index: 293323 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.0510. Min Act: -0.0001

Data Index: 1217933 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9511. Min Act: -0.0001

Data Index: 8334 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9080. Min Act: -0.0001

Data Index: 24619 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.0257. Min Act: -0.0001

Data Index: 138942 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.1042. Min Act: -0.0001

Data Index: 945140 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.1393. Min Act: -0.0001

Data Index: 401846 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9064. Min Act: -0.0001

Data Index: 880092 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 3.5804. Min Range: -3.5804

Max Act: 2.1063. Min Act: -0.0001

Data Index: 1236643 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9902. Min Act: -0.0001

Data Index: 1069981 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9903. Min Act: -0.0001

Data Index: 372796 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.8722. Min Act: -0.0001

Data Index: 1634813 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9948. Min Act: -0.0001

Data Index: 495023 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9682. Min Act: -0.0001

Data Index: 1157390 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.5804. Min Range: -3.5804

Max Act: 1.9811. Min Act: -0.0001

Data Index: 1626703 (Python Code)

Max Activating Token Index: 473