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

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

Neuron 5613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1433422 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1614510 (Python Code)

Max Activating Token Index: 612

Text #2

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.5002. Min Act: -0.0000

Data Index: 189021 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1572532 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1446034 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4696. Min Act: -0.0000

Data Index: 439949 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4758. Min Act: -0.0000

Data Index: 829430 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1640060 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1506436 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4452. Min Act: -0.0000

Data Index: 883819 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4290. Min Act: -0.0000

Data Index: 257944 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4236. Min Act: -0.0000

Data Index: 246822 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4509. Min Act: -0.0000

Data Index: 317786 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1356338 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1241350 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1113729 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1522200 (Python Code)

Max Activating Token Index: 318

Text #17

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4094. Min Act: -0.0000

Data Index: 734710 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4105. Min Act: -0.0000

Data Index: 413239 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.5456. Min Range: -0.5456

Max Act: 0.4073. Min Act: -0.0000

Data Index: 723602 (C4 (Web Text))

Max Activating Token Index: 400