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

Dataset: The Pile

Neuron 4070 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: 0.7026. Min Range: -0.7026

Max Act: 0.7026. Min Act: -0.0000

Data Index: 363624 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1799029 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1905961 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1983447 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1905661 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1710085 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4950. Min Act: -0.0000

Data Index: 144454 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4959. Min Act: -0.0000

Data Index: 259904 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1041421 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1396232 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1720678 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4700. Min Act: -0.0000

Data Index: 253704 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4851. Min Act: -0.0000

Data Index: 817323 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1908557 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4706. Min Act: -0.0000

Data Index: 691838 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4915. Min Act: -0.0000

Data Index: 827763 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1920744 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4343. Min Act: -0.0000

Data Index: 662240 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1020750 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.7026. Min Range: -0.7026

Max Act: 0.4780. Min Act: -0.0000

Data Index: 276092 (The Pile)

Max Activating Token Index: 108