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

Dataset: The Pile

Neuron 61 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1443648 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1985505 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1102735 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4078. Min Act: -0.0000

Data Index: 801740 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3924. Min Act: -0.0000

Data Index: 197427 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1043359 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3660. Min Act: -0.0000

Data Index: 360211 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3944. Min Act: 0.0000

Data Index: 116860 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3988. Min Act: -0.0000

Data Index: 383788 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1396136 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3365. Min Act: -0.0000

Data Index: 562618 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1136447 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3563. Min Act: -0.0000

Data Index: 384399 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1583685 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1906726 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3561. Min Act: -0.0000

Data Index: 929095 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1620745 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1087197 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3500. Min Act: -0.0000

Data Index: 768898 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3405. Min Act: -0.0000

Data Index: 375467 (The Pile)

Max Activating Token Index: 673