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

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

Neuron 5228 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2185. Min Range: -3.2185

Max Act: 3.2185. Min Act: -0.0000

Data Index: 894934 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 3.2185. Min Range: -3.2185

Max Act: 3.1082. Min Act: -0.0000

Data Index: 723398 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.7167. Min Act: -0.0000

Data Index: 1234206 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.9307. Min Act: -0.0000

Data Index: 861394 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.7534. Min Act: -0.0000

Data Index: 1060501 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.7517. Min Act: -0.0000

Data Index: 190379 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.9068. Min Act: -0.0000

Data Index: 877959 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1338096 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.6822. Min Act: -0.0000

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.6127. Min Act: -0.0000

Data Index: 1114358 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.6121. Min Act: -0.0000

Data Index: 1091563 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5073. Min Act: -0.0000

Data Index: 183873 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5849. Min Act: -0.0000

Data Index: 344416 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5620. Min Act: -0.0000

Data Index: 481516 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.4427. Min Act: -0.0000

Data Index: 826909 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5438. Min Act: -0.0000

Data Index: 286276 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5270. Min Act: -0.0000

Data Index: 129059 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5161. Min Act: -0.0000

Data Index: 893020 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.5059. Min Act: -0.0000

Data Index: 917799 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.2185. Min Range: -3.2185

Max Act: 2.4705. Min Act: -0.0000

Data Index: 520997 (C4 (Web Text))

Max Activating Token Index: 872