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

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

Neuron 4570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.7027. Min Act: -0.0000

Data Index: 533916 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.7214. Min Act: -0.0000

Data Index: 113296 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.5815. Min Act: -0.0000

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4287. Min Act: -0.0000

Data Index: 624554 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.6320. Min Act: -0.0000

Data Index: 1225050 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.6223. Min Act: -0.0000

Data Index: 323828 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4903. Min Act: -0.0000

Data Index: 35202 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1013756 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2894. Min Act: -0.0000

Data Index: 849915 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4221. Min Act: -0.0000

Data Index: 136049 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1013619 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4776. Min Act: -0.0000

Data Index: 97441 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4855. Min Act: -0.0000

Data Index: 617986 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.3081. Min Act: -0.0000

Data Index: 620119 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.3911. Min Act: -0.0000

Data Index: 442171 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4280. Min Act: -0.0000

Data Index: 48350 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2611. Min Act: -0.0000

Data Index: 1238171 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1352530 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.2367. Min Act: -0.0000

Data Index: 5081 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.7214. Min Range: -1.7214

Max Act: 1.4809. Min Act: -0.0000

Data Index: 222995 (C4 (Web Text))

Max Activating Token Index: 284