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

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

Neuron 627 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3822. Min Act: -0.0001

Data Index: 61580 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1214824 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.4287. Min Act: -0.0001

Data Index: 1219455 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.4421. Min Act: -0.0001

Data Index: 843176 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.4097. Min Act: -0.0001

Data Index: 576957 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3632. Min Act: -0.0001

Data Index: 1341196 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3961. Min Act: -0.0001

Data Index: 1385398 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3783. Min Act: -0.0001

Data Index: 153103 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3506. Min Act: -0.0001

Data Index: 1653545 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3737. Min Act: -0.0001

Data Index: 645816 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3431. Min Act: -0.0001

Data Index: 285681 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3653. Min Act: -0.0001

Data Index: 123470 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3521. Min Act: -0.0001

Data Index: 1050899 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3307. Min Act: -0.0001

Data Index: 204739 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3416. Min Act: -0.0001

Data Index: 793200 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3374. Min Act: -0.0001

Data Index: 937806 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3648. Min Act: -0.0001

Data Index: 1640243 (Python Code)

Max Activating Token Index: 512

Text #17

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3513. Min Act: -0.0001

Data Index: 907619 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3267. Min Act: -0.0001

Data Index: 943019 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3471. Min Act: -0.0001

Data Index: 829770 (C4 (Web Text))

Max Activating Token Index: 620