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

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

Neuron 5143 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: 5.7170. Min Range: -5.7170

Max Act: 5.7170. Min Act: -0.0000

Data Index: 302516 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.5857. Min Act: -0.0000

Data Index: 265775 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.5673. Min Act: -0.0000

Data Index: 1091225 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.2731. Min Act: -0.0000

Data Index: 833182 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.0230. Min Act: -0.0000

Data Index: 1191466 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.0303. Min Act: -0.0000

Data Index: 667739 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.9913. Min Act: -0.0000

Data Index: 463577 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.3090. Min Act: -0.0000

Data Index: 425096 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.9240. Min Act: -0.0000

Data Index: 576313 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 5.7170. Min Range: -5.7170

Max Act: 5.0727. Min Act: -0.0000

Data Index: 1286947 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.8986. Min Act: -0.0000

Data Index: 43285 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.9353. Min Act: -0.0000

Data Index: 1152121 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.8854. Min Act: -0.0000

Data Index: 259911 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.8655. Min Act: -0.0000

Data Index: 941628 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.8422. Min Act: -0.0000

Data Index: 20789 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.5700. Min Act: -0.0000

Data Index: 1229903 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.9500. Min Act: -0.0000

Data Index: 579015 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.7182. Min Act: -0.0000

Data Index: 1058746 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.7348. Min Act: -0.0000

Data Index: 931983 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 5.7170. Min Range: -5.7170

Max Act: 4.7060. Min Act: -0.0000

Data Index: 683828 (C4 (Web Text))

Max Activating Token Index: 139