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

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

Neuron 1668 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: 1.3313. Min Range: -1.3313

Max Act: 1.3313. Min Act: -0.0001

Data Index: 424732 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1527. Min Act: -0.0001

Data Index: 1136594 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1793. Min Act: -0.0001

Data Index: 856242 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1208879 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.1073. Min Act: -0.0001

Data Index: 1084199 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.3313. Min Range: -1.3313

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1153159 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9500. Min Act: -0.0001

Data Index: 720754 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9380. Min Act: -0.0001

Data Index: 843694 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1022352 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9190. Min Act: -0.0001

Data Index: 1094837 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9486. Min Act: -0.0001

Data Index: 275907 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8723. Min Act: -0.0001

Data Index: 360064 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8344. Min Act: -0.0001

Data Index: 973313 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8848. Min Act: -0.0001

Data Index: 276358 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8804. Min Act: -0.0001

Data Index: 349240 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8515. Min Act: -0.0001

Data Index: 3567 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8996. Min Act: -0.0001

Data Index: 649641 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9311. Min Act: -0.0001

Data Index: 849102 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.8892. Min Act: -0.0001

Data Index: 624821 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.3313. Min Range: -1.3313

Max Act: 0.9156. Min Act: -0.0001

Data Index: 1177347 (C4 (Web Text))

Max Activating Token Index: 496