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

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

Neuron 4060 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.5096. Min Act: -0.0000

Data Index: 935395 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2219. Min Act: -0.0000

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.3160. Min Act: -0.0000

Data Index: 441198 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2399. Min Act: -0.0000

Data Index: 688600 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1560. Min Act: -0.0000

Data Index: 283085 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1045444 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2143. Min Act: -0.0000

Data Index: 162156 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1173962 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2116. Min Act: -0.0000

Data Index: 933308 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1185. Min Act: -0.0000

Data Index: 897085 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1215419 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2518. Min Act: -0.0000

Data Index: 188549 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.0322. Min Act: -0.0000

Data Index: 594950 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1643. Min Act: -0.0000

Data Index: 547955 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1304. Min Act: -0.0000

Data Index: 632900 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1468. Min Act: -0.0000

Data Index: 64537 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1318. Min Act: -0.0000

Data Index: 138684 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.2070. Min Act: -0.0000

Data Index: 635128 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.5096. Min Range: -1.5096

Max Act: 1.1468. Min Act: -0.0000

Data Index: 716989 (C4 (Web Text))

Max Activating Token Index: 198