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

Dataset: The Pile

Neuron 1267 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: 0.7024. Min Range: -0.7024

Max Act: 0.7024. Min Act: -0.0000

Data Index: 51511 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4902. Min Act: -0.0000

Data Index: 167534 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4550. Min Act: -0.0000

Data Index: 428321 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1260292 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1084804 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3850. Min Act: -0.0000

Data Index: 185167 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1422156 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1592474 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1517599 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1246533 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1098446 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1686273 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3605. Min Act: -0.0000

Data Index: 318963 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1676101 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3456. Min Act: -0.0000

Data Index: 889152 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3546. Min Act: -0.0000

Data Index: 740656 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3537. Min Act: -0.0000

Data Index: 628331 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3369. Min Act: -0.0000

Data Index: 956033 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1813247 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.7024. Min Range: -0.7024

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1474477 (The Pile)

Max Activating Token Index: 775