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

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

Neuron 4572 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: 2.4511. Min Range: -2.4511

Max Act: 2.4381. Min Act: -0.0000

Data Index: 1064920 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.4511. Min Act: -0.0000

Data Index: 782623 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.3576. Min Act: -0.0000

Data Index: 553890 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.3064. Min Act: -0.0000

Data Index: 460029 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.2786. Min Act: -0.0000

Data Index: 139466 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.1781. Min Act: -0.0000

Data Index: 1328913 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.0409. Min Act: -0.0000

Data Index: 120354 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.0397. Min Act: -0.0000

Data Index: 341397 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.9117. Min Act: -0.0000

Data Index: 33178 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.0178. Min Act: -0.0000

Data Index: 1290360 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1101809 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.9168. Min Act: -0.0000

Data Index: 444131 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.4511. Min Range: -2.4511

Max Act: 2.0161. Min Act: -0.0000

Data Index: 760287 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.7997. Min Act: -0.0000

Data Index: 877767 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.8889. Min Act: -0.0000

Data Index: 296235 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.8796. Min Act: -0.0000

Data Index: 797836 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.9619. Min Act: -0.0000

Data Index: 456326 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.9632. Min Act: -0.0000

Data Index: 689952 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.8565. Min Act: -0.0000

Data Index: 268728 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 2.4511. Min Range: -2.4511

Max Act: 1.8360. Min Act: -0.0000

Data Index: 1318387 (C4 (Web Text))

Max Activating Token Index: 660