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

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

Neuron 1820 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.7161. Min Act: -0.0000

Data Index: 45855 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.7622. Min Act: -0.0000

Data Index: 988465 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.3790. Min Act: -0.0000

Data Index: 1182335 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.5167. Min Act: -0.0000

Data Index: 1069743 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.2653. Min Act: -0.0000

Data Index: 590577 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.3903. Min Act: -0.0000

Data Index: 527726 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.2152. Min Act: -0.0000

Data Index: 56698 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.2996. Min Act: -0.0000

Data Index: 890624 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.2270. Min Act: -0.0000

Data Index: 1084727 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.1926. Min Act: -0.0000

Data Index: 1110727 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.3074. Min Act: -0.0000

Data Index: 34826 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 4.7622. Min Range: -4.7622

Max Act: 4.0137. Min Act: -0.0000

Data Index: 280902 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.8903. Min Act: -0.0000

Data Index: 552748 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.6771. Min Act: -0.0000

Data Index: 1138846 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.9732. Min Act: -0.0000

Data Index: 122818 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.7997. Min Act: -0.0000

Data Index: 709683 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.5052. Min Act: -0.0000

Data Index: 899848 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.6267. Min Act: -0.0000

Data Index: 975867 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.6117. Min Act: -0.0000

Data Index: 1164875 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.7622. Min Range: -4.7622

Max Act: 3.6079. Min Act: -0.0000

Data Index: 75252 (C4 (Web Text))

Max Activating Token Index: 101