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

Dataset: The Pile

Neuron 359 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: 0.6591. Min Range: -0.6591

Max Act: 0.6591. Min Act: -0.0000

Data Index: 598650 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1271535 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1116800 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1257465 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1608617 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4863. Min Act: -0.0000

Data Index: 952727 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1941087 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4225. Min Act: -0.0000

Data Index: 220531 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1323793 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1089032 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4469. Min Act: -0.0000

Data Index: 725396 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4327. Min Act: 0.0000

Data Index: 1443116 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1629235 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4393. Min Act: -0.0000

Data Index: 317695 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1919946 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4095. Min Act: -0.0000

Data Index: 295333 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1957621 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4476. Min Act: -0.0000

Data Index: 314390 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1160160 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 0.6591. Min Range: -0.6591

Max Act: 0.4110. Min Act: -0.0000

Data Index: 297369 (The Pile)

Max Activating Token Index: 453