Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7820. Min Act: -0.0000

Data Index: 646582 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7664. Min Act: -0.0000

Data Index: 427690 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7642. Min Act: -0.0000

Data Index: 107778 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1302331 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7368. Min Act: -0.0000

Data Index: 248470 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1470071 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7044. Min Act: -0.0000

Data Index: 420492 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6969. Min Act: -0.0000

Data Index: 717360 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7191. Min Act: -0.0000

Data Index: 588045 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7172. Min Act: -0.0000

Data Index: 867374 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6917. Min Act: -0.0000

Data Index: 210695 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6862. Min Act: -0.0000

Data Index: 147328 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6629. Min Act: -0.0000

Data Index: 66417 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7472. Min Act: -0.0000

Data Index: 613379 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1867518 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1513384 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1375708 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.7111. Min Act: -0.0000

Data Index: 572255 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6887. Min Act: -0.0000

Data Index: 546088 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.8055. Min Range: -0.8055

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1819673 (The Pile)

Max Activating Token Index: 227