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

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

Neuron 1977 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5391. Min Range: -2.5391

Max Act: 2.5391. Min Act: -0.0000

Data Index: 1273814 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 2.5391. Min Range: -2.5391

Max Act: 2.4996. Min Act: -0.0000

Data Index: 115810 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.7535. Min Act: -0.0000

Data Index: 1176394 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.8830. Min Act: -0.0000

Data Index: 1290743 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1321721 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.6823. Min Act: -0.0000

Data Index: 379162 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.7071. Min Act: -0.0000

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.6980. Min Act: -0.0000

Data Index: 252547 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.7173. Min Act: -0.0000

Data Index: 924124 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.5710. Min Act: -0.0000

Data Index: 240526 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.7567. Min Act: -0.0000

Data Index: 1007807 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.5289. Min Act: -0.0000

Data Index: 689152 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.5321. Min Act: -0.0000

Data Index: 1439826 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1636411 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.4932. Min Act: -0.0000

Data Index: 665225 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.6068. Min Act: -0.0000

Data Index: 1122048 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.5576. Min Act: -0.0000

Data Index: 1271376 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.6735. Min Act: -0.0000

Data Index: 951350 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.6197. Min Act: -0.0000

Data Index: 1175195 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 2.5391. Min Range: -2.5391

Max Act: 1.5624. Min Act: -0.0000

Data Index: 978092 (C4 (Web Text))

Max Activating Token Index: 625