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

Dataset: The Pile

Neuron 2801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1249865 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1615236 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5871. Min Act: -0.0000

Data Index: 296869 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.6033. Min Act: -0.0000

Data Index: 954320 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5571. Min Act: -0.0000

Data Index: 224078 (The Pile)

Max Activating Token Index: 267

Text #5

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5555. Min Act: -0.0000

Data Index: 491113 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1046850 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1757302 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5434. Min Act: -0.0000

Data Index: 354059 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1673729 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5463. Min Act: -0.0000

Data Index: 455548 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4959. Min Act: -0.0000

Data Index: 420421 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1664113 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1971321 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5167. Min Act: -0.0000

Data Index: 340463 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1913832 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5142. Min Act: -0.0000

Data Index: 317812 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.4991. Min Act: -0.0000

Data Index: 691855 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1822508 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.6590. Min Range: -0.6590

Max Act: 0.5475. Min Act: -0.0000

Data Index: 383154 (The Pile)

Max Activating Token Index: 511