Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 14.4225. Min Range: -14.4225

Max Act: 14.4225. Min Act: -0.0000

Data Index: 576033 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 14.4225. Min Range: -14.4225

Max Act: 13.8347. Min Act: -0.0000

Data Index: 1055844 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 14.4225. Min Range: -14.4225

Max Act: 13.7284. Min Act: -0.0000

Data Index: 904748 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 14.4225. Min Range: -14.4225

Max Act: 13.8254. Min Act: -0.0000

Data Index: 1183270 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 14.4225. Min Range: -14.4225

Max Act: 13.7727. Min Act: -0.0000

Data Index: 188895 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 14.4225. Min Range: -14.4225

Max Act: 13.3658. Min Act: -0.0000

Data Index: 740391 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 14.4225. Min Range: -14.4225

Max Act: 13.4623. Min Act: -0.0000

Data Index: 294737 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.8224. Min Act: -0.0000

Data Index: 1105580 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.6118. Min Act: -0.0000

Data Index: 760891 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.8085. Min Act: -0.0000

Data Index: 689035 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.5284. Min Act: -0.0000

Data Index: 1102529 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.6658. Min Act: -0.0000

Data Index: 974295 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.3538. Min Act: -0.0000

Data Index: 273621 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.2444. Min Act: -0.0000

Data Index: 299217 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.5560. Min Act: -0.0000

Data Index: 260631 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.4661. Min Act: -0.0000

Data Index: 714777 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.3427. Min Act: -0.0000

Data Index: 850064 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.3054. Min Act: -0.0000

Data Index: 1341581 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 14.4225. Min Range: -14.4225

Max Act: 11.9128. Min Act: -0.0000

Data Index: 545366 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 14.4225. Min Range: -14.4225

Max Act: 12.2417. Min Act: -0.0000

Data Index: 919969 (C4 (Web Text))

Max Activating Token Index: 226