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

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

Neuron 4914 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.4484. Min Act: -0.0000

Data Index: 767916 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.2362. Min Act: -0.0000

Data Index: 696148 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.2353. Min Act: -0.0000

Data Index: 742180 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1335123 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.1282. Min Act: -0.0000

Data Index: 302926 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.1116. Min Act: -0.0000

Data Index: 339872 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.0741. Min Act: -0.0000

Data Index: 239624 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.9541. Min Act: -0.0000

Data Index: 539071 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 2.4484. Min Range: -2.4484

Max Act: 2.0927. Min Act: -0.0000

Data Index: 600049 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.9628. Min Act: -0.0000

Data Index: 194457 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.9626. Min Act: -0.0000

Data Index: 758582 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.9544. Min Act: -0.0000

Data Index: 1058960 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.9131. Min Act: -0.0000

Data Index: 132946 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.8722. Min Act: -0.0000

Data Index: 146945 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.8608. Min Act: -0.0000

Data Index: 144835 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.7432. Min Act: -0.0000

Data Index: 1133784 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.7315. Min Act: -0.0000

Data Index: 814860 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.7323. Min Act: -0.0000

Data Index: 717993 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.7011. Min Act: -0.0000

Data Index: 801571 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 2.4484. Min Range: -2.4484

Max Act: 1.6882. Min Act: -0.0000

Data Index: 708013 (C4 (Web Text))

Max Activating Token Index: 107