Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8366. Min Act: -0.0002

Data Index: 770417 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8664. Min Act: -0.0002

Data Index: 734656 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8092. Min Act: -0.0001

Data Index: 582108 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8539. Min Act: -0.0002

Data Index: 44192 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7539. Min Act: -0.0001

Data Index: 676006 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8190. Min Act: -0.0001

Data Index: 790834 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7841. Min Act: -0.0001

Data Index: 100753 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8053. Min Act: -0.0001

Data Index: 991489 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7503. Min Act: -0.0002

Data Index: 1122916 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7339. Min Act: -0.0002

Data Index: 790572 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7014. Min Act: -0.0002

Data Index: 423092 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7079. Min Act: -0.0002

Data Index: 645662 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7049. Min Act: -0.0001

Data Index: 850107 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6797. Min Act: -0.0002

Data Index: 959831 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6993. Min Act: -0.0002

Data Index: 824387 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6987. Min Act: -0.0001

Data Index: 850325 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6585. Min Act: -0.0001

Data Index: 928785 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6894. Min Act: -0.0001

Data Index: 132058 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7486. Min Act: -0.0001

Data Index: 323682 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1002350 (C4 (Web Text))

Max Activating Token Index: 330