Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2142 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.4897. Min Act: -0.0000

Data Index: 327718 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1272121 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.1965. Min Act: -0.0000

Data Index: 930765 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.1887. Min Act: -0.0000

Data Index: 1834903 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.1208. Min Act: 0.0001

Data Index: 696793 (The Pile)

Max Activating Token Index: 572

Text #5

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9956. Min Act: -0.0000

Data Index: 771425 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1145386 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 1.4897. Min Range: -1.4897

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1249748 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1547299 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1739741 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9388. Min Act: -0.0000

Data Index: 232174 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1890637 (The Pile)

Max Activating Token Index: 972

Text #12

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9212. Min Act: -0.0000

Data Index: 470394 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8881. Min Act: -0.0000

Data Index: 773902 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9073. Min Act: -0.0000

Data Index: 326840 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1127682 (The Pile)

Max Activating Token Index: 347

Text #16

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8723. Min Act: -0.0000

Data Index: 699581 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1637124 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1440216 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 1.4897. Min Range: -1.4897

Max Act: 0.7662. Min Act: -0.0000

Data Index: 779957 (The Pile)

Max Activating Token Index: 496