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

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

Neuron 602 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3219. Min Range: -1.3219

Max Act: 1.3219. Min Act: -0.0000

Data Index: 353993 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1212430 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.9048. Min Act: -0.0000

Data Index: 647611 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.7743. Min Act: -0.0000

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.7195. Min Act: -0.0000

Data Index: 520809 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.7233. Min Act: -0.0000

Data Index: 37674 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5947. Min Act: -0.0000

Data Index: 312941 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6286. Min Act: -0.0000

Data Index: 143727 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6740. Min Act: -0.0000

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6217. Min Act: -0.0000

Data Index: 820625 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1148320 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6273. Min Act: -0.0000

Data Index: 994212 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5983. Min Act: -0.0000

Data Index: 361617 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6502. Min Act: -0.0000

Data Index: 257519 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.6183. Min Act: -0.0000

Data Index: 545214 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5724. Min Act: -0.0000

Data Index: 83983 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1165654 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5818. Min Act: -0.0000

Data Index: 181767 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5598. Min Act: -0.0000

Data Index: 612008 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 1.3219. Min Range: -1.3219

Max Act: 0.5713. Min Act: -0.0000

Data Index: 87762 (C4 (Web Text))

Max Activating Token Index: 498