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

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

Neuron 1805 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: 1.2830. Min Range: -1.2830

Max Act: 1.2113. Min Act: -0.0001

Data Index: 59651 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.2830. Min Act: -0.0001

Data Index: 1238081 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.2558. Min Act: -0.0001

Data Index: 972876 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.2265. Min Act: -0.0001

Data Index: 819507 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.1400. Min Act: -0.0001

Data Index: 1023151 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.1422. Min Act: -0.0001

Data Index: 636055 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0997. Min Act: -0.0001

Data Index: 1152621 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0690. Min Act: -0.0001

Data Index: 831124 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9944. Min Act: -0.0001

Data Index: 880603 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0494. Min Act: -0.0001

Data Index: 900265 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0343. Min Act: -0.0001

Data Index: 457599 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9939. Min Act: -0.0001

Data Index: 421167 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9760. Min Act: -0.0001

Data Index: 985370 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9955. Min Act: -0.0001

Data Index: 300935 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0549. Min Act: -0.0001

Data Index: 91701 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0194. Min Act: -0.0001

Data Index: 1114760 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9309. Min Act: -0.0001

Data Index: 253887 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9972. Min Act: -0.0001

Data Index: 1240027 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.2830. Min Range: -1.2830

Max Act: 1.0613. Min Act: -0.0001

Data Index: 147675 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.2830. Min Range: -1.2830

Max Act: 0.9077. Min Act: -0.0001

Data Index: 783418 (C4 (Web Text))

Max Activating Token Index: 283