Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1485 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1516937 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1273046 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.6057. Min Act: -0.0000

Data Index: 621045 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1733750 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.6318. Min Act: -0.0000

Data Index: 969801 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5851. Min Act: -0.0000

Data Index: 64080 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1102378 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5016. Min Act: -0.0000

Data Index: 863723 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1777932 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5328. Min Act: -0.0000

Data Index: 239991 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1903869 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1058926 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1210337 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5217. Min Act: 0.0000

Data Index: 764856 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5148. Min Act: -0.0000

Data Index: 663923 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1901285 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1243586 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.4890. Min Act: 0.0000

Data Index: 1463227 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.4637. Min Act: -0.0000

Data Index: 860632 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1223964 (The Pile)

Max Activating Token Index: 976