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

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

Neuron 1157 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4727. Min Act: -0.0000

Data Index: 977531 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.5002. Min Act: 0.0000

Data Index: 127819 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1173821 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4965. Min Act: 0.0000

Data Index: 498806 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1316030 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4335. Min Act: 0.0000

Data Index: 980362 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3988. Min Act: 0.0000

Data Index: 388652 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3745. Min Act: -0.0000

Data Index: 320859 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3837. Min Act: -0.0000

Data Index: 740610 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1314678 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3634. Min Act: 0.0000

Data Index: 1314732 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3362. Min Act: -0.0000

Data Index: 543915 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3170. Min Act: -0.0000

Data Index: 772782 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3075. Min Act: -0.0000

Data Index: 17101 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3132. Min Act: 0.0000

Data Index: 972454 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1331975 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1155526 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.2988. Min Act: 0.0000

Data Index: 490318 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.2731. Min Act: -0.0000

Data Index: 306667 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1054034 (C4 (Web Text))

Max Activating Token Index: 388