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

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

Neuron 266 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.6158. Min Act: -0.0001

Data Index: 207834 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.3574. Min Act: -0.0001

Data Index: 1295738 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1383. Min Act: -0.0001

Data Index: 991875 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.2664. Min Act: -0.0001

Data Index: 696979 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.2170. Min Act: -0.0001

Data Index: 783386 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1688. Min Act: -0.0001

Data Index: 169436 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1727. Min Act: -0.0001

Data Index: 1123294 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1789. Min Act: -0.0001

Data Index: 342613 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0613. Min Act: -0.0001

Data Index: 923880 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0828. Min Act: -0.0001

Data Index: 1204596 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0520. Min Act: -0.0001

Data Index: 23406 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0930. Min Act: -0.0001

Data Index: 667005 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1176. Min Act: -0.0001

Data Index: 770702 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0199. Min Act: -0.0001

Data Index: 32210 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0363. Min Act: -0.0001

Data Index: 400642 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.1365. Min Act: -0.0001

Data Index: 743606 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0794. Min Act: -0.0001

Data Index: 999191 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0731. Min Act: -0.0001

Data Index: 1052768 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.6158. Min Range: -1.6158

Max Act: 0.9307. Min Act: -0.0001

Data Index: 871027 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.6158. Min Range: -1.6158

Max Act: 1.0547. Min Act: -0.0001

Data Index: 1481187 (Python Code)

Max Activating Token Index: 381