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

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

Neuron 649 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8443. Min Act: -0.0000

Data Index: 120323 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9028. Min Act: -0.0000

Data Index: 588012 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9186. Min Act: -0.0000

Data Index: 654842 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1199246 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8844. Min Act: -0.0000

Data Index: 348428 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1003719 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7396. Min Act: -0.0000

Data Index: 802518 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7472. Min Act: -0.0000

Data Index: 721061 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1177170 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7585. Min Act: -0.0000

Data Index: 559545 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1354687 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6778. Min Act: -0.0000

Data Index: 831785 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6705. Min Act: -0.0000

Data Index: 404823 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6782. Min Act: -0.0000

Data Index: 568539 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5079. Min Act: -0.0000

Data Index: 114839 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6537. Min Act: -0.0000

Data Index: 52022 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6281. Min Act: -0.0000

Data Index: 161953 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5824. Min Act: -0.0000

Data Index: 804319 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5644. Min Act: -0.0000

Data Index: 309032 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1303519 (C4 (Web Text))

Max Activating Token Index: 735