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

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

Neuron 2702 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.5687. Min Act: -0.0000

Data Index: 533379 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1222113 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.2054. Min Act: -0.0000

Data Index: 379042 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0751. Min Act: -0.0000

Data Index: 217169 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0992. Min Act: -0.0000

Data Index: 871629 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1331292 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0708. Min Act: -0.0000

Data Index: 555799 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0963. Min Act: -0.0000

Data Index: 405300 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1093062 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1030025 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9923. Min Act: -0.0000

Data Index: 590538 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9812. Min Act: -0.0000

Data Index: 969414 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0162. Min Act: -0.0000

Data Index: 893654 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1077514 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9897. Min Act: -0.0000

Data Index: 522246 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9535. Min Act: -0.0000

Data Index: 455392 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.5687. Min Range: -1.5687

Max Act: 1.0176. Min Act: -0.0000

Data Index: 484762 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.9466. Min Act: -0.0000

Data Index: 104590 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.8117. Min Act: -0.0000

Data Index: 33034 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.5687. Min Range: -1.5687

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1018008 (C4 (Web Text))

Max Activating Token Index: 461