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

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

Neuron 5662 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.2452. Min Range: -3.2452

Max Act: 3.2452. Min Act: -0.0002

Data Index: 538641 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.2452. Min Range: -3.2452

Max Act: 3.0521. Min Act: -0.0002

Data Index: 840250 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.9952. Min Act: -0.0002

Data Index: 96162 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.9836. Min Act: -0.0002

Data Index: 1042209 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.9179. Min Act: -0.0002

Data Index: 223686 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.8573. Min Act: -0.0002

Data Index: 454500 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.8916. Min Act: -0.0003

Data Index: 147367 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.9584. Min Act: -0.0002

Data Index: 406572 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.7896. Min Act: -0.0002

Data Index: 400363 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.8710. Min Act: -0.0002

Data Index: 545795 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.7009. Min Act: -0.0002

Data Index: 1065043 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6675. Min Act: -0.0002

Data Index: 290888 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.7428. Min Act: -0.0002

Data Index: 686465 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.7404. Min Act: -0.0002

Data Index: 815814 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6810. Min Act: -0.0002

Data Index: 670831 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6036. Min Act: -0.0002

Data Index: 849874 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.7137. Min Act: -0.0002

Data Index: 676494 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6438. Min Act: -0.0002

Data Index: 1332917 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6362. Min Act: -0.0003

Data Index: 1322683 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6553. Min Act: -0.0002

Data Index: 1189754 (C4 (Web Text))

Max Activating Token Index: 822