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

Dataset: The Pile

Neuron 3412 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: 0.5450. Min Range: -0.5450

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1671183 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1065070 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4423. Min Act: -0.0000

Data Index: 565882 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4316. Min Act: 0.0000

Data Index: 132684 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4348. Min Act: -0.0000

Data Index: 220339 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3969. Min Act: -0.0000

Data Index: 979624 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3916. Min Act: -0.0000

Data Index: 642941 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4013. Min Act: -0.0000

Data Index: 852112 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1858584 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3863. Min Act: 0.0000

Data Index: 1093156 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3712. Min Act: -0.0000

Data Index: 114580 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3947. Min Act: 0.0000

Data Index: 1889731 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3686. Min Act: -0.0000

Data Index: 203971 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1122508 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3772. Min Act: -0.0000

Data Index: 177576 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3743. Min Act: -0.0000

Data Index: 589576 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3550. Min Act: -0.0000

Data Index: 270044 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3538. Min Act: -0.0000

Data Index: 203368 (The Pile)

Max Activating Token Index: 983

Text #18

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3637. Min Act: -0.0000

Data Index: 15582 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.3204. Min Act: -0.0000

Data Index: 580541 (The Pile)

Max Activating Token Index: 434