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

Dataset: The Pile

Neuron 4095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.6407. Min Act: -0.0000

Data Index: 1742641 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1061950 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.1697. Min Act: -0.0000

Data Index: 766332 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.0513. Min Act: -0.0000

Data Index: 227993 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.0531. Min Act: -0.0000

Data Index: 414034 (The Pile)

Max Activating Token Index: 99

Text #5

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1804445 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9818. Min Act: -0.0000

Data Index: 809778 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1031307 (The Pile)

Max Activating Token Index: 144

Text #8

Max Range: 1.6407. Min Range: -1.6407

Max Act: 1.0312. Min Act: -0.0000

Data Index: 445586 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9729. Min Act: -0.0000

Data Index: 439329 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1779796 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1682105 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1840772 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.8732. Min Act: -0.0000

Data Index: 36666 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1293989 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.8850. Min Act: -0.0000

Data Index: 509792 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1658992 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.8109. Min Act: -0.0000

Data Index: 550095 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1542607 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 1.6407. Min Range: -1.6407

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1467705 (The Pile)

Max Activating Token Index: 535