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

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

Neuron 3078 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.2453. Min Act: -0.0001

Data Index: 1202527 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.2180. Min Act: -0.0001

Data Index: 1076504 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1635. Min Act: -0.0001

Data Index: 1113236 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1087. Min Act: -0.0001

Data Index: 1098704 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.9776. Min Act: -0.0001

Data Index: 1240108 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.9532. Min Act: -0.0001

Data Index: 261025 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1108. Min Act: -0.0001

Data Index: 15453 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.2307. Min Act: -0.0001

Data Index: 445104 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0826. Min Act: -0.0001

Data Index: 197695 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0825. Min Act: -0.0001

Data Index: 1013020 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0804. Min Act: -0.0001

Data Index: 84585 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0669. Min Act: -0.0001

Data Index: 1110667 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0811. Min Act: -0.0001

Data Index: 982652 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.2167. Min Act: -0.0001

Data Index: 1029102 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0676. Min Act: -0.0001

Data Index: 1294091 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.9792. Min Act: -0.0001

Data Index: 1127532 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.8402. Min Act: -0.0001

Data Index: 580291 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.9836. Min Act: -0.0001

Data Index: 940566 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 3.2453. Min Range: -3.2453

Max Act: 2.9523. Min Act: -0.0001

Data Index: 98611 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1023. Min Act: -0.0001

Data Index: 1268712 (C4 (Web Text))

Max Activating Token Index: 561