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

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

Neuron 5223 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2808. Min Range: -4.2808

Max Act: 4.2808. Min Act: -0.0000

Data Index: 1500649 (Python Code)

Max Activating Token Index: 989

Text #1

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.6209. Min Act: -0.0000

Data Index: 392798 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.7056. Min Act: -0.0000

Data Index: 759499 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.3769. Min Act: -0.0000

Data Index: 830829 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1294383 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.2295. Min Act: -0.0000

Data Index: 155146 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.1988. Min Act: -0.0000

Data Index: 663388 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.1459. Min Act: -0.0000

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.1919. Min Act: -0.0000

Data Index: 161290 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.0345. Min Act: -0.0000

Data Index: 1550050 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.0271. Min Act: -0.0000

Data Index: 158080 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 4.2808. Min Range: -4.2808

Max Act: 3.0038. Min Act: -0.0000

Data Index: 1016497 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.9894. Min Act: -0.0000

Data Index: 207942 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.8185. Min Act: -0.0000

Data Index: 395538 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.9585. Min Act: -0.0000

Data Index: 815371 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.7469. Min Act: -0.0000

Data Index: 901133 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.6233. Min Act: -0.0000

Data Index: 1559310 (Python Code)

Max Activating Token Index: 602

Text #17

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.8730. Min Act: -0.0000

Data Index: 434599 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.8305. Min Act: -0.0000

Data Index: 908915 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 4.2808. Min Range: -4.2808

Max Act: 2.7029. Min Act: -0.0000

Data Index: 193378 (C4 (Web Text))

Max Activating Token Index: 788