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

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

Neuron 2306 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0677. Min Range: -3.0677

Max Act: 3.0677. Min Act: -0.0000

Data Index: 1524363 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.8685. Min Act: 0.0000

Data Index: 1366672 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.8104. Min Act: -0.0000

Data Index: 1421461 (Python Code)

Max Activating Token Index: 998

Text #3

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.7555. Min Act: -0.0000

Data Index: 1441852 (Python Code)

Max Activating Token Index: 971

Text #4

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.3908. Min Act: -0.0000

Data Index: 353422 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5312. Min Act: -0.0000

Data Index: 202147 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5119. Min Act: -0.0000

Data Index: 661824 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1509796 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5574. Min Act: 0.0003

Data Index: 1426403 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5109. Min Act: -0.0000

Data Index: 318472 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5003. Min Act: -0.0000

Data Index: 707454 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1381863 (Python Code)

Max Activating Token Index: 110

Text #12

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.3714. Min Act: -0.0000

Data Index: 195499 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5433. Min Act: -0.0000

Data Index: 1096696 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.3650. Min Act: 0.0000

Data Index: 1443292 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1431560 (Python Code)

Max Activating Token Index: 833

Text #16

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1550861 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.2840. Min Act: -0.0000

Data Index: 707327 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.3190. Min Act: -0.0000

Data Index: 617022 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.2766. Min Act: -0.0000

Data Index: 321312 (C4 (Web Text))

Max Activating Token Index: 373