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

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

Neuron 5960 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: 4.4097. Min Range: -4.4097

Max Act: 4.4097. Min Act: -0.0000

Data Index: 825810 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 4.4097. Min Range: -4.4097

Max Act: 4.0723. Min Act: -0.0000

Data Index: 705348 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 4.4097. Min Range: -4.4097

Max Act: 3.8154. Min Act: -0.0000

Data Index: 326199 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.6103. Min Act: -0.0000

Data Index: 650307 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.5860. Min Act: -0.0000

Data Index: 729138 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.2729. Min Act: -0.0000

Data Index: 21702 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1223. Min Act: -0.0000

Data Index: 1000655 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1971. Min Act: -0.0000

Data Index: 748290 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1751. Min Act: -0.0000

Data Index: 387231 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1664. Min Act: -0.0000

Data Index: 34218 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1468. Min Act: -0.0000

Data Index: 770049 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.2678. Min Act: -0.0000

Data Index: 390273 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 4.4097. Min Range: -4.4097

Max Act: 1.9787. Min Act: -0.0000

Data Index: 538873 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1107. Min Act: -0.0000

Data Index: 855563 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1056. Min Act: -0.0000

Data Index: 928588 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.0937. Min Act: -0.0000

Data Index: 145333 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 4.4097. Min Range: -4.4097

Max Act: 1.9668. Min Act: -0.0000

Data Index: 741675 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 4.4097. Min Range: -4.4097

Max Act: 2.1248. Min Act: -0.0000

Data Index: 1522688 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 4.4097. Min Range: -4.4097

Max Act: 1.8898. Min Act: -0.0000

Data Index: 29703 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 4.4097. Min Range: -4.4097

Max Act: 1.9875. Min Act: -0.0000

Data Index: 63327 (C4 (Web Text))

Max Activating Token Index: 177