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

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

Neuron 3835 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: 1.3995. Min Range: -1.3995

Max Act: 1.3995. Min Act: -0.0001

Data Index: 692095 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.2089. Min Act: -0.0001

Data Index: 649154 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.2313. Min Act: -0.0001

Data Index: 402504 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.0577. Min Act: -0.0001

Data Index: 944675 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.0728. Min Act: -0.0001

Data Index: 830651 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.0301. Min Act: -0.0001

Data Index: 1232015 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.0316. Min Act: -0.0001

Data Index: 165908 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.3995. Min Range: -1.3995

Max Act: 1.0165. Min Act: -0.0001

Data Index: 1137729 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9686. Min Act: -0.0001

Data Index: 760267 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9989. Min Act: -0.0001

Data Index: 169240 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9626. Min Act: -0.0001

Data Index: 1102176 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9783. Min Act: -0.0001

Data Index: 305973 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9775. Min Act: -0.0001

Data Index: 631275 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9302. Min Act: -0.0001

Data Index: 361368 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9089. Min Act: -0.0001

Data Index: 1053979 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9385. Min Act: -0.0001

Data Index: 60486 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.9225. Min Act: -0.0001

Data Index: 504324 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.8473. Min Act: -0.0001

Data Index: 1082924 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.8960. Min Act: -0.0001

Data Index: 783080 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.3995. Min Range: -1.3995

Max Act: 0.8591. Min Act: -0.0001

Data Index: 47617 (C4 (Web Text))

Max Activating Token Index: 299