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

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

Neuron 6098 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: 2.9953. Min Range: -2.9953

Max Act: 2.9953. Min Act: -0.0000

Data Index: 289498 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.9717. Min Act: -0.0000

Data Index: 167522 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.7728. Min Act: -0.0000

Data Index: 1231559 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.6220. Min Act: -0.0000

Data Index: 669265 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.5095. Min Act: -0.0000

Data Index: 987869 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.5953. Min Act: -0.0000

Data Index: 954710 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1203936 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.6709. Min Act: -0.0000

Data Index: 1189461 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.5242. Min Act: -0.0000

Data Index: 1066575 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.5092. Min Act: -0.0000

Data Index: 35163 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.5145. Min Act: -0.0000

Data Index: 1106858 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.4978. Min Act: -0.0000

Data Index: 252308 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.4967. Min Act: -0.0000

Data Index: 917983 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.5538. Min Act: -0.0000

Data Index: 824746 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.4921. Min Act: -0.0000

Data Index: 350491 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.2020. Min Act: -0.0000

Data Index: 393792 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.2307. Min Act: -0.0000

Data Index: 1328497 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.3153. Min Act: -0.0000

Data Index: 1038013 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.4484. Min Act: -0.0000

Data Index: 1046320 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 2.9953. Min Range: -2.9953

Max Act: 2.3121. Min Act: -0.0000

Data Index: 17479 (C4 (Web Text))

Max Activating Token Index: 122