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

Dataset: The Pile

Neuron 410 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: 0.5724. Min Range: -0.5724

Max Act: 0.5724. Min Act: -0.0000

Data Index: 587197 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.5151. Min Act: 0.0001

Data Index: 1959764 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1114398 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4494. Min Act: -0.0000

Data Index: 895512 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1695811 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4395. Min Act: -0.0000

Data Index: 943218 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1856670 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3588. Min Act: -0.0000

Data Index: 215094 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3579. Min Act: -0.0000

Data Index: 562380 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3698. Min Act: -0.0000

Data Index: 474336 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1741106 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3510. Min Act: -0.0000

Data Index: 297789 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3390. Min Act: -0.0000

Data Index: 157725 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.4092. Min Act: -0.0000

Data Index: 246815 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1251631 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1820815 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1958601 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3432. Min Act: -0.0000

Data Index: 148914 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1106999 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.5724. Min Range: -0.5724

Max Act: 0.3611. Min Act: -0.0000

Data Index: 882217 (The Pile)

Max Activating Token Index: 505