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

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

Neuron 2108 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.9258. Min Act: -0.0000

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.8222. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.8327. Min Act: -0.0000

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.7806. Min Act: -0.0000

Data Index: 711857 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6925. Min Act: -0.0000

Data Index: 23609 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6726. Min Act: -0.0000

Data Index: 520714 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1164423 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6195. Min Act: -0.0000

Data Index: 458950 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6275. Min Act: -0.0000

Data Index: 298175 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1136538 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1000784 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6427. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6632. Min Act: -0.0000

Data Index: 48044 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6265. Min Act: -0.0000

Data Index: 447167 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6235. Min Act: -0.0000

Data Index: 191040 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6008. Min Act: -0.0000

Data Index: 162592 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1106759 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.7769. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.9258. Min Range: -0.9258

Max Act: 0.5772. Min Act: -0.0000

Data Index: 653373 (C4 (Web Text))

Max Activating Token Index: 647