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

Dataset: The Pile

Neuron 3441 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1568600 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1797. Min Act: -0.0000

Data Index: 340984 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1598. Min Act: -0.0000

Data Index: 176517 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1710. Min Act: -0.0000

Data Index: 529561 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1177587 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1617682 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1569. Min Act: -0.0000

Data Index: 989568 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1579. Min Act: -0.0000

Data Index: 643038 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1004173 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1505. Min Act: -0.0000

Data Index: 184676 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1485. Min Act: -0.0000

Data Index: 847899 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1510. Min Act: -0.0000

Data Index: 228873 (The Pile)

Max Activating Token Index: 683

Text #12

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1639238 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.0996. Min Act: -0.0000

Data Index: 599285 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1383. Min Act: -0.0000

Data Index: 673092 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1657695 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1266515 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1255885 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1146187 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1997542 (The Pile)

Max Activating Token Index: 996