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

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

Neuron 3217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6120. Min Act: -0.0000

Data Index: 179262 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6130. Min Act: -0.0000

Data Index: 801490 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1149898 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6010. Min Act: -0.0000

Data Index: 5407 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1268330 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6019. Min Act: -0.0000

Data Index: 329111 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1046456 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5865. Min Act: -0.0000

Data Index: 405980 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5353. Min Act: -0.0000

Data Index: 313536 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5615. Min Act: -0.0000

Data Index: 251926 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5255. Min Act: -0.0000

Data Index: 964777 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5136. Min Act: -0.0000

Data Index: 872800 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5080. Min Act: -0.0000

Data Index: 244776 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5256. Min Act: -0.0000

Data Index: 678912 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4977. Min Act: -0.0000

Data Index: 876702 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4669. Min Act: -0.0000

Data Index: 642848 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4990. Min Act: -0.0000

Data Index: 728749 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1081320 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4771. Min Act: -0.0000

Data Index: 247284 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.4498. Min Act: -0.0000

Data Index: 769940 (C4 (Web Text))

Max Activating Token Index: 223