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

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

Neuron 214 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: 2.1374. Min Range: -2.1374

Max Act: 2.1374. Min Act: -0.0000

Data Index: 914599 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.7057. Min Act: -0.0000

Data Index: 968107 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.7382. Min Act: -0.0000

Data Index: 657812 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.7080. Min Act: -0.0000

Data Index: 163894 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.5589. Min Act: -0.0000

Data Index: 186250 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.5600. Min Act: -0.0000

Data Index: 752375 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4701. Min Act: -0.0000

Data Index: 315951 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.5280. Min Act: -0.0000

Data Index: 300966 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4503. Min Act: -0.0000

Data Index: 493635 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.6056. Min Act: -0.0000

Data Index: 1272043 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4106. Min Act: -0.0000

Data Index: 316270 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4870. Min Act: -0.0000

Data Index: 555799 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4833. Min Act: -0.0000

Data Index: 537070 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1097393 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.3911. Min Act: -0.0000

Data Index: 569506 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1233554 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.5146. Min Act: -0.0000

Data Index: 1341831 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.2575. Min Act: -0.0000

Data Index: 595426 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4179. Min Act: -0.0000

Data Index: 477859 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 2.1374. Min Range: -2.1374

Max Act: 1.4751. Min Act: -0.0000

Data Index: 529230 (C4 (Web Text))

Max Activating Token Index: 45