Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3861 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8449. Min Act: -0.0000

Data Index: 291550 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1004557 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1682477 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7851. Min Act: -0.0000

Data Index: 887287 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1441811 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1700799 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7293. Min Act: -0.0000

Data Index: 984343 (The Pile)

Max Activating Token Index: 801

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1362229 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1274570 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7374. Min Act: -0.0000

Data Index: 661702 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1479644 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7160. Min Act: -0.0000

Data Index: 25388 (The Pile)

Max Activating Token Index: 686

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1381149 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.5626. Min Act: -0.0000

Data Index: 513941 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7132. Min Act: -0.0000

Data Index: 160252 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1857627 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6190. Min Act: -0.0000

Data Index: 683807 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1663678 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6921. Min Act: -0.0000

Data Index: 768788 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6053. Min Act: -0.0000

Data Index: 51219 (The Pile)

Max Activating Token Index: 800