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

Dataset: The Pile

Neuron 803 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: 0.4376. Min Range: -0.4376

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1134437 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4024. Min Act: -0.0000

Data Index: 196518 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4376. Min Act: -0.0000

Data Index: 259703 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3619. Min Act: -0.0000

Data Index: 160043 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1938231 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3761. Min Act: -0.0000

Data Index: 562630 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3985. Min Act: -0.0000

Data Index: 643321 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1413403 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3397. Min Act: -0.0000

Data Index: 923203 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3414. Min Act: -0.0000

Data Index: 718886 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3362. Min Act: -0.0000

Data Index: 247164 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1895797 (The Pile)

Max Activating Token Index: 752

Text #12

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3320. Min Act: -0.0000

Data Index: 630967 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1579683 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3239. Min Act: -0.0000

Data Index: 14896 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1357622 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3221. Min Act: -0.0000

Data Index: 135292 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3182. Min Act: -0.0000

Data Index: 854727 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1834935 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1759498 (The Pile)

Max Activating Token Index: 187