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

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

Neuron 477 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: 2.4259. Min Range: -2.4259

Max Act: 2.4259. Min Act: -0.0000

Data Index: 390325 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.3935. Min Act: -0.0000

Data Index: 379125 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.4155. Min Act: -0.0000

Data Index: 432537 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.2807. Min Act: -0.0000

Data Index: 40592 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.9808. Min Act: -0.0000

Data Index: 346259 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.1869. Min Act: -0.0000

Data Index: 924913 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.0741. Min Act: -0.0000

Data Index: 134298 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.1254. Min Act: -0.0000

Data Index: 838318 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.8624. Min Act: -0.0000

Data Index: 825695 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.9696. Min Act: -0.0000

Data Index: 435942 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.1309. Min Act: -0.0000

Data Index: 1052733 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.0140. Min Act: -0.0000

Data Index: 1321305 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.4259. Min Range: -2.4259

Max Act: 2.1078. Min Act: -0.0000

Data Index: 890549 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.8726. Min Act: -0.0000

Data Index: 1283774 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.9297. Min Act: -0.0000

Data Index: 721532 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.8943. Min Act: -0.0000

Data Index: 632039 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.8335. Min Act: -0.0000

Data Index: 594927 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.8104. Min Act: -0.0000

Data Index: 264369 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.7079. Min Act: -0.0000

Data Index: 816205 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 2.4259. Min Range: -2.4259

Max Act: 1.9552. Min Act: -0.0000

Data Index: 356023 (C4 (Web Text))

Max Activating Token Index: 741