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

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

Neuron 1432 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: 2.6872. Min Range: -2.6872

Max Act: 2.6872. Min Act: -0.0000

Data Index: 1534044 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 2.6872. Min Range: -2.6872

Max Act: 2.2784. Min Act: -0.0000

Data Index: 1513666 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 2.6872. Min Range: -2.6872

Max Act: 2.2648. Min Act: -0.0000

Data Index: 1577721 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 2.6872. Min Range: -2.6872

Max Act: 2.2534. Min Act: -0.0000

Data Index: 1369940 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 2.6872. Min Range: -2.6872

Max Act: 2.0654. Min Act: -0.0000

Data Index: 1631918 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 2.6872. Min Range: -2.6872

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1647278 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 2.6872. Min Range: -2.6872

Max Act: 2.0211. Min Act: -0.0000

Data Index: 1568457 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.9120. Min Act: -0.0000

Data Index: 1480318 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.9656. Min Act: -0.0000

Data Index: 1432735 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.8987. Min Act: -0.0000

Data Index: 1541340 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1440292 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.9762. Min Act: -0.0000

Data Index: 1496742 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.8165. Min Act: -0.0000

Data Index: 1490196 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1438008 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.8785. Min Act: -0.0000

Data Index: 1436337 (Python Code)

Max Activating Token Index: 995

Text #15

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.7809. Min Act: -0.0000

Data Index: 1464663 (Python Code)

Max Activating Token Index: 745

Text #16

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.8128. Min Act: -0.0000

Data Index: 1509288 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1478349 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1465332 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 2.6872. Min Range: -2.6872

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1657091 (Python Code)

Max Activating Token Index: 973