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

Dataset: The Pile

Neuron 2549 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: 0.4786. Min Range: -0.4786

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1680541 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1813994 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4445. Min Act: -0.0000

Data Index: 806730 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4384. Min Act: -0.0000

Data Index: 991315 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1306142 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3992. Min Act: -0.0000

Data Index: 673400 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4058. Min Act: 0.0000

Data Index: 107669 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3869. Min Act: -0.0000

Data Index: 278343 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1182324 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4003. Min Act: 0.0000

Data Index: 1427498 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3584. Min Act: -0.0000

Data Index: 142597 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1560634 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1825520 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3448. Min Act: 0.0000

Data Index: 1589793 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3467. Min Act: 0.0000

Data Index: 1397489 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3464. Min Act: -0.0000

Data Index: 76028 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3369. Min Act: -0.0000

Data Index: 563645 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3255. Min Act: -0.0000

Data Index: 70184 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1292510 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1198233 (The Pile)

Max Activating Token Index: 309