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

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

Neuron 3040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.6065. Min Act: -0.0001

Data Index: 396058 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.7173. Min Act: -0.0001

Data Index: 1203323 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.6586. Min Act: -0.0001

Data Index: 894963 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.6602. Min Act: -0.0001

Data Index: 840177 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.5806. Min Act: -0.0001

Data Index: 713898 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4259. Min Act: -0.0001

Data Index: 778312 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.5967. Min Act: -0.0001

Data Index: 619279 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4285. Min Act: -0.0001

Data Index: 571316 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.5490. Min Act: -0.0001

Data Index: 1195166 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4618. Min Act: -0.0001

Data Index: 312777 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4685. Min Act: -0.0001

Data Index: 1309180 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4805. Min Act: -0.0001

Data Index: 324772 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4307. Min Act: -0.0001

Data Index: 303408 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.5118. Min Act: -0.0001

Data Index: 1053942 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.3850. Min Act: -0.0001

Data Index: 642061 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.3536. Min Act: -0.0001

Data Index: 5251 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4640. Min Act: -0.0001

Data Index: 555592 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.5121. Min Act: -0.0001

Data Index: 54060 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4697. Min Act: -0.0001

Data Index: 196678 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.7173. Min Range: -1.7173

Max Act: 1.4693. Min Act: -0.0001

Data Index: 582000 (C4 (Web Text))

Max Activating Token Index: 1004