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

Dataset: The Pile

Neuron 222 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: 0.4403. Min Range: -0.4403

Max Act: 0.4328. Min Act: -0.0000

Data Index: 23478 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4403. Min Act: -0.0000

Data Index: 878125 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3933. Min Act: -0.0000

Data Index: 578938 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.4177. Min Act: -0.0000

Data Index: 109251 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3626. Min Act: -0.0000

Data Index: 298344 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1027234 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1081329 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1089774 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3535. Min Act: -0.0000

Data Index: 144418 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3235. Min Act: -0.0000

Data Index: 94817 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3629. Min Act: -0.0000

Data Index: 752722 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3446. Min Act: -0.0000

Data Index: 90615 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1258881 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1671724 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1487760 (The Pile)

Max Activating Token Index: 60

Text #15

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1790572 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3196. Min Act: -0.0000

Data Index: 124704 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1411345 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1074700 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.4403. Min Range: -0.4403

Max Act: 0.3433. Min Act: -0.0000

Data Index: 233274 (The Pile)

Max Activating Token Index: 720