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

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

Neuron 2626 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.6684. Min Act: -0.0001

Data Index: 697126 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.7086. Min Act: -0.0001

Data Index: 223100 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.5353. Min Act: -0.0001

Data Index: 1064391 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.6160. Min Act: -0.0001

Data Index: 1060394 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.5293. Min Act: -0.0001

Data Index: 656974 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4226. Min Act: -0.0001

Data Index: 363177 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.6762. Min Act: -0.0000

Data Index: 75439 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1203975 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4844. Min Act: -0.0001

Data Index: 169597 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4701. Min Act: -0.0001

Data Index: 191755 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4748. Min Act: -0.0001

Data Index: 189358 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.5532. Min Act: -0.0001

Data Index: 36619 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4688. Min Act: -0.0001

Data Index: 845915 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4109. Min Act: -0.0001

Data Index: 980517 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.3996. Min Act: -0.0001

Data Index: 1214306 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4725. Min Act: -0.0001

Data Index: 1028696 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4563. Min Act: -0.0001

Data Index: 119294 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.6065. Min Act: -0.0001

Data Index: 953761 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.4563. Min Act: -0.0001

Data Index: 390676 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.7086. Min Range: -1.7086

Max Act: 1.3664. Min Act: -0.0001

Data Index: 1312281 (C4 (Web Text))

Max Activating Token Index: 958