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

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

Neuron 3505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.4742. Min Act: -0.0002

Data Index: 936563 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.3555. Min Act: -0.0002

Data Index: 274581 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0722. Min Act: -0.0001

Data Index: 615823 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2518. Min Act: -0.0001

Data Index: 214643 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1664. Min Act: -0.0001

Data Index: 483411 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2147. Min Act: -0.0001

Data Index: 190913 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1974. Min Act: -0.0002

Data Index: 1019916 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0672. Min Act: -0.0001

Data Index: 27160 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.1910. Min Act: -0.0001

Data Index: 958569 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0194. Min Act: -0.0001

Data Index: 1083973 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9775. Min Act: -0.0001

Data Index: 1154569 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9722. Min Act: -0.0001

Data Index: 400409 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2542. Min Act: -0.0001

Data Index: 698284 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0169. Min Act: -0.0001

Data Index: 223624 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.8841. Min Act: -0.0001

Data Index: 562525 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9957. Min Act: -0.0002

Data Index: 958396 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 1.4742. Min Range: -1.4742

Max Act: 0.9892. Min Act: -0.0001

Data Index: 1331680 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.2648. Min Act: -0.0001

Data Index: 696335 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0865. Min Act: -0.0001

Data Index: 1121072 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 1.4742. Min Range: -1.4742

Max Act: 1.0171. Min Act: -0.0001

Data Index: 1496190 (Python Code)

Max Activating Token Index: 83