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

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

Neuron 179 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: 1.1145. Min Range: -1.1145

Max Act: 1.1145. Min Act: 0.0000

Data Index: 384851 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.1145. Min Range: -1.1145

Max Act: 1.0122. Min Act: -0.0000

Data Index: 417128 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9457. Min Act: 0.0000

Data Index: 328536 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9156. Min Act: -0.0000

Data Index: 175313 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8830. Min Act: -0.0000

Data Index: 323817 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8756. Min Act: 0.0000

Data Index: 490615 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8185. Min Act: -0.0000

Data Index: 220900 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1082122 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7207. Min Act: -0.0000

Data Index: 507585 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.7559. Min Act: -0.0000

Data Index: 371208 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6694. Min Act: -0.0000

Data Index: 220760 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6022. Min Act: -0.0000

Data Index: 269219 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1151356 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.5839. Min Act: 0.0001

Data Index: 310032 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6180. Min Act: -0.0000

Data Index: 485986 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.5934. Min Act: 0.0000

Data Index: 704391 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.5899. Min Act: -0.0000

Data Index: 505056 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.6095. Min Act: 0.0000

Data Index: 861552 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.5832. Min Act: -0.0000

Data Index: 12968 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.5808. Min Act: 0.0000

Data Index: 386248 (C4 (Web Text))

Max Activating Token Index: 411