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

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

Neuron 4530 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: 1.4000. Min Range: -1.4000

Max Act: 1.4000. Min Act: -0.0000

Data Index: 195192 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.3190. Min Act: -0.0000

Data Index: 345645 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.3619. Min Act: -0.0000

Data Index: 966596 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1565. Min Act: -0.0000

Data Index: 130728 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0986. Min Act: -0.0000

Data Index: 709178 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1291. Min Act: -0.0000

Data Index: 565166 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.1124. Min Act: -0.0000

Data Index: 181381 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0935. Min Act: -0.0000

Data Index: 339375 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0567. Min Act: -0.0000

Data Index: 320218 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.4000. Min Range: -1.4000

Max Act: 1.0453. Min Act: -0.0000

Data Index: 294830 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8645. Min Act: -0.0000

Data Index: 248314 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1230076 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1253141 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.8176. Min Act: -0.0000

Data Index: 674503 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1156879 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.7690. Min Act: -0.0000

Data Index: 962155 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1048785 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.7907. Min Act: -0.0000

Data Index: 345469 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.7835. Min Act: -0.0000

Data Index: 336327 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.4000. Min Range: -1.4000

Max Act: 0.7299. Min Act: -0.0000

Data Index: 7762 (C4 (Web Text))

Max Activating Token Index: 501