Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.3240. Min Act: -0.0000

Data Index: 315973 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1300041 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1035877 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.0139. Min Act: -0.0000

Data Index: 425950 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.0734. Min Act: -0.0000

Data Index: 379073 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.1028. Min Act: -0.0000

Data Index: 172002 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.0394. Min Act: -0.0000

Data Index: 558101 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.3240. Min Range: -1.3240

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1101109 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8352. Min Act: -0.0000

Data Index: 534346 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8743. Min Act: -0.0000

Data Index: 807036 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.9183. Min Act: -0.0000

Data Index: 997335 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8597. Min Act: -0.0000

Data Index: 950949 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1221059 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8330. Min Act: -0.0000

Data Index: 644658 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1111791 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1106297 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8995. Min Act: -0.0000

Data Index: 954526 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1255447 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1013258 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.3240. Min Range: -1.3240

Max Act: 0.8773. Min Act: -0.0000

Data Index: 327768 (C4 (Web Text))

Max Activating Token Index: 51