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

Dataset: The Pile

Neuron 3076 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: 1.3671. Min Range: -1.3671

Max Act: 1.3671. Min Act: -0.0000

Data Index: 481667 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0555. Min Act: -0.0000

Data Index: 759683 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1551374 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9442. Min Act: -0.0000

Data Index: 782578 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0431. Min Act: -0.0000

Data Index: 597751 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1771684 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8856. Min Act: -0.0000

Data Index: 854573 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1428616 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9961. Min Act: -0.0000

Data Index: 963212 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9351. Min Act: -0.0000

Data Index: 68730 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1307312 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1378990 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1711576 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1997364 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1746068 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1936547 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8664. Min Act: -0.0000

Data Index: 414775 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1477345 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8797. Min Act: -0.0000

Data Index: 966516 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 1.3671. Min Range: -1.3671

Max Act: 0.8017. Min Act: -0.0000

Data Index: 599556 (The Pile)

Max Activating Token Index: 697