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

Dataset: The Pile

Neuron 517 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: 0.5654. Min Range: -0.5654

Max Act: 0.5654. Min Act: -0.0000

Data Index: 425595 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4488. Min Act: -0.0000

Data Index: 341265 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1525121 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3571. Min Act: -0.0000

Data Index: 811773 (The Pile)

Max Activating Token Index: 670

Text #4

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1657592 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1249523 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3264. Min Act: -0.0000

Data Index: 3330 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1889275 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1664825 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1089832 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1113328 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1017657 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2906. Min Act: -0.0000

Data Index: 646509 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1229084 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1431358 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1170938 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1961921 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1992836 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1227512 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.2567. Min Act: -0.0000

Data Index: 82380 (The Pile)

Max Activating Token Index: 539