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

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

Neuron 1407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.5535. Min Act: -0.0000

Data Index: 1015411 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.3593. Min Act: -0.0000

Data Index: 1097249 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.5937. Min Act: -0.0000

Data Index: 205575 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.2338. Min Act: -0.0000

Data Index: 783824 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.4408. Min Act: -0.0000

Data Index: 1162710 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.3546. Min Act: -0.0000

Data Index: 1148669 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.5430. Min Act: -0.0000

Data Index: 1325545 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.2696. Min Act: -0.0000

Data Index: 301118 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.3452. Min Act: -0.0000

Data Index: 415669 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.2889. Min Act: -0.0000

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.2750. Min Act: -0.0000

Data Index: 83685 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.1321. Min Act: -0.0000

Data Index: 1255798 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.0177. Min Act: -0.0000

Data Index: 32917 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.0196. Min Act: -0.0000

Data Index: 52326 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.7107. Min Act: -0.0000

Data Index: 55167 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.9757. Min Act: -0.0000

Data Index: 589140 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 2.5937. Min Range: -2.5937

Max Act: 2.0761. Min Act: -0.0000

Data Index: 1160349 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.8954. Min Act: -0.0000

Data Index: 578114 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.7855. Min Act: -0.0000

Data Index: 779280 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 2.5937. Min Range: -2.5937

Max Act: 1.8876. Min Act: -0.0000

Data Index: 773078 (C4 (Web Text))

Max Activating Token Index: 639