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

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

Neuron 299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1073787 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3837. Min Act: -0.0001

Data Index: 1444569 (Python Code)

Max Activating Token Index: 170

Text #2

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3455. Min Act: -0.0000

Data Index: 907748 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3471. Min Act: -0.0001

Data Index: 856633 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3197. Min Act: -0.0001

Data Index: 556638 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1592236 (Python Code)

Max Activating Token Index: 135

Text #6

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3249. Min Act: -0.0001

Data Index: 253743 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3435. Min Act: -0.0001

Data Index: 816144 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1162941 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3166. Min Act: -0.0001

Data Index: 102042 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3202. Min Act: -0.0000

Data Index: 9699 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3187. Min Act: -0.0001

Data Index: 754831 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3164. Min Act: -0.0000

Data Index: 427761 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1087265 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2899. Min Act: -0.0000

Data Index: 132882 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2996. Min Act: -0.0001

Data Index: 2725 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3205. Min Act: -0.0000

Data Index: 733749 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2992. Min Act: -0.0001

Data Index: 77623 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3171. Min Act: -0.0001

Data Index: 315132 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3163. Min Act: -0.0001

Data Index: 1554464 (Python Code)

Max Activating Token Index: 563