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

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

Neuron 1681 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: 3.6074. Min Range: -3.6074

Max Act: 3.6074. Min Act: -0.0000

Data Index: 898867 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 3.6074. Min Range: -3.6074

Max Act: 3.5550. Min Act: -0.0000

Data Index: 1268319 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 3.6074. Min Range: -3.6074

Max Act: 3.2340. Min Act: -0.0000

Data Index: 1027511 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.6074. Min Range: -3.6074

Max Act: 3.0547. Min Act: -0.0000

Data Index: 495395 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 3.6074. Min Range: -3.6074

Max Act: 3.2995. Min Act: -0.0000

Data Index: 641056 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.6730. Min Act: -0.0000

Data Index: 131779 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.7048. Min Act: -0.0000

Data Index: 969783 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1278765 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.4410. Min Act: -0.0000

Data Index: 42635 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.4442. Min Act: -0.0000

Data Index: 146778 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.5517. Min Act: -0.0000

Data Index: 754560 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.5532. Min Act: -0.0000

Data Index: 1174605 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.5119. Min Act: -0.0000

Data Index: 1128112 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.4600. Min Act: -0.0000

Data Index: 1272187 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.4338. Min Act: -0.0000

Data Index: 1342241 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.4105. Min Act: -0.0000

Data Index: 398750 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.3657. Min Act: -0.0000

Data Index: 410617 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.4751. Min Act: -0.0000

Data Index: 103044 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.3241. Min Act: -0.0000

Data Index: 1285416 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 3.6074. Min Range: -3.6074

Max Act: 2.1302. Min Act: -0.0000

Data Index: 406222 (C4 (Web Text))

Max Activating Token Index: 887