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

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

Neuron 952 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9608. Min Range: -1.9608

Max Act: 1.9608. Min Act: -0.0000

Data Index: 156802 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.9608. Min Range: -1.9608

Max Act: 1.0724. Min Act: 0.0000

Data Index: 29565 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.9866. Min Act: 0.0000

Data Index: 348746 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.9608. Min Range: -1.9608

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1162853 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1008510 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1314416 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7998. Min Act: 0.0000

Data Index: 1103594 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.8752. Min Act: -0.0000

Data Index: 779992 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.8612. Min Act: 0.0000

Data Index: 840168 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.8736. Min Act: 0.0000

Data Index: 1175872 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.9140. Min Act: -0.0000

Data Index: 817653 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.8265. Min Act: -0.0000

Data Index: 32081 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7237. Min Act: 0.0000

Data Index: 181460 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7940. Min Act: -0.0000

Data Index: 470432 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7626. Min Act: -0.0000

Data Index: 260231 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7991. Min Act: -0.0000

Data Index: 809217 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7626. Min Act: -0.0000

Data Index: 509162 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7431. Min Act: -0.0000

Data Index: 675880 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1433806 (Python Code)

Max Activating Token Index: 874

Text #19

Max Range: 1.9608. Min Range: -1.9608

Max Act: 0.7188. Min Act: -0.0000

Data Index: 485929 (C4 (Web Text))

Max Activating Token Index: 224