Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0867. Min Range: -1.0867

Max Act: 1.0867. Min Act: -0.0001

Data Index: 1204733 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.0867. Min Range: -1.0867

Max Act: 1.0144. Min Act: -0.0001

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.0867. Min Range: -1.0867

Max Act: 1.0379. Min Act: -0.0001

Data Index: 2683 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1180238 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.0867. Min Range: -1.0867

Max Act: 1.0028. Min Act: -0.0001

Data Index: 676946 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9290. Min Act: -0.0001

Data Index: 783783 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9553. Min Act: -0.0001

Data Index: 188249 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9571. Min Act: -0.0001

Data Index: 820022 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9470. Min Act: -0.0001

Data Index: 540980 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9514. Min Act: -0.0001

Data Index: 926740 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9733. Min Act: -0.0001

Data Index: 579495 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.8774. Min Act: -0.0001

Data Index: 813354 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.8936. Min Act: -0.0001

Data Index: 567274 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9165. Min Act: -0.0001

Data Index: 320289 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9228. Min Act: -0.0001

Data Index: 1298002 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.8965. Min Act: -0.0001

Data Index: 1004682 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9191. Min Act: -0.0001

Data Index: 403617 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9666. Min Act: -0.0001

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.8552. Min Act: -0.0001

Data Index: 476836 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.0867. Min Range: -1.0867

Max Act: 0.9051. Min Act: -0.0001

Data Index: 1125976 (C4 (Web Text))

Max Activating Token Index: 76