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

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

Neuron 3376 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3970. Min Act: -0.0002

Data Index: 773063 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3623. Min Act: -0.0002

Data Index: 1023907 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3363. Min Act: -0.0002

Data Index: 331380 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3481. Min Act: -0.0002

Data Index: 770988 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3618. Min Act: -0.0002

Data Index: 989438 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3219. Min Act: -0.0002

Data Index: 1183237 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2965. Min Act: -0.0002

Data Index: 2216 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2980. Min Act: -0.0002

Data Index: 1063286 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2900. Min Act: -0.0002

Data Index: 645893 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3030. Min Act: -0.0002

Data Index: 468422 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2642. Min Act: -0.0002

Data Index: 1326899 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2775. Min Act: -0.0002

Data Index: 1337091 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2528. Min Act: -0.0002

Data Index: 204689 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2496. Min Act: -0.0002

Data Index: 374241 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2649. Min Act: -0.0002

Data Index: 865385 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2282. Min Act: -0.0002

Data Index: 369103 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2508. Min Act: -0.0002

Data Index: 1187306 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2167. Min Act: -0.0002

Data Index: 61011 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1064970 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.2014. Min Act: -0.0002

Data Index: 821146 (C4 (Web Text))

Max Activating Token Index: 771