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

Dataset: The Pile

Neuron 1652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1836609 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1937968 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1748843 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3876. Min Act: -0.0000

Data Index: 757538 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.4113. Min Act: -0.0000

Data Index: 700245 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1871142 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3950. Min Act: -0.0001

Data Index: 1436797 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3819. Min Act: -0.0000

Data Index: 62358 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3713. Min Act: -0.0000

Data Index: 504506 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1686578 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3675. Min Act: -0.0001

Data Index: 290517 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1506965 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3764. Min Act: -0.0000

Data Index: 202145 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3745. Min Act: -0.0000

Data Index: 947702 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3663. Min Act: -0.0001

Data Index: 51855 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3367. Min Act: -0.0000

Data Index: 465353 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3486. Min Act: -0.0000

Data Index: 984604 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3628. Min Act: -0.0000

Data Index: 403830 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1309631 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 0.4550. Min Range: -0.4550

Max Act: 0.3409. Min Act: -0.0000

Data Index: 751807 (The Pile)

Max Activating Token Index: 405