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

Dataset: The Pile

Neuron 274 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1670844 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.9849. Min Act: -0.0000

Data Index: 728462 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1779809 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8435. Min Act: -0.0000

Data Index: 1612659 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1037331 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8414. Min Act: -0.0000

Data Index: 435404 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7743. Min Act: -0.0000

Data Index: 956429 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1748124 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8181. Min Act: -0.0000

Data Index: 80610 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1961216 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7645. Min Act: -0.0000

Data Index: 794682 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7688. Min Act: -0.0000

Data Index: 805400 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1702384 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1778343 (The Pile)

Max Activating Token Index: 802

Text #14

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7912. Min Act: -0.0000

Data Index: 836221 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.6405. Min Act: -0.0000

Data Index: 773061 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1085227 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7704. Min Act: -0.0000

Data Index: 399241 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1904070 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.9960. Min Range: -0.9960

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1464912 (The Pile)

Max Activating Token Index: 426