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

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

Neuron 4503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.5562. Min Act: -0.0000

Data Index: 926607 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3108. Min Act: -0.0000

Data Index: 825269 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.8775. Min Act: -0.0000

Data Index: 175495 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.5124. Min Act: -0.0000

Data Index: 1215335 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4749. Min Act: -0.0001

Data Index: 339126 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4542. Min Act: -0.0000

Data Index: 897997 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4790. Min Act: -0.0000

Data Index: 1028336 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4604. Min Act: -0.0001

Data Index: 611044 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4230. Min Act: -0.0000

Data Index: 1079133 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4969. Min Act: -0.0000

Data Index: 1192977 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.4805. Min Act: -0.0000

Data Index: 696833 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.3579. Min Act: -0.0001

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.3931. Min Act: -0.0000

Data Index: 987924 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.1256. Min Act: -0.0000

Data Index: 582677 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.2658. Min Act: -0.0000

Data Index: 734410 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.2547. Min Act: -0.0000

Data Index: 710995 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.3319. Min Act: -0.0000

Data Index: 1012825 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.3004. Min Act: -0.0000

Data Index: 470472 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.2561. Min Act: -0.0000

Data Index: 453766 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.1394. Min Act: -0.0000

Data Index: 388034 (C4 (Web Text))

Max Activating Token Index: 853