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

Dataset: The Pile

Neuron 1276 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: 0.7595. Min Range: -0.7595

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1813533 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1596873 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6800. Min Act: -0.0000

Data Index: 267 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.7595. Min Act: -0.0000

Data Index: 953728 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1548993 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1031928 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1852530 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1575246 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.6216. Min Act: -0.0000

Data Index: 740250 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1010456 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1401875 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5545. Min Act: -0.0000

Data Index: 912534 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5844. Min Act: -0.0000

Data Index: 121688 (The Pile)

Max Activating Token Index: 187

Text #13

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4959. Min Act: -0.0000

Data Index: 493580 (The Pile)

Max Activating Token Index: 546

Text #14

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5387. Min Act: -0.0000

Data Index: 558555 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1692644 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5992. Min Act: -0.0000

Data Index: 227276 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5457. Min Act: -0.0000

Data Index: 165075 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.5350. Min Act: -0.0000

Data Index: 54677 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 0.7595. Min Range: -0.7595

Max Act: 0.4655. Min Act: -0.0000

Data Index: 291924 (The Pile)

Max Activating Token Index: 286