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

Dataset: The Pile

Neuron 3319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3466. Min Act: -0.0000

Data Index: 707639 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1713147 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3478. Min Act: -0.0000

Data Index: 368698 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3317. Min Act: -0.0000

Data Index: 673985 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3197. Min Act: -0.0000

Data Index: 828349 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1608208 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2952. Min Act: -0.0000

Data Index: 569527 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1782603 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3200. Min Act: -0.0000

Data Index: 579057 (The Pile)

Max Activating Token Index: 97

Text #9

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3172. Min Act: -0.0000

Data Index: 235252 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1501345 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2963. Min Act: -0.0000

Data Index: 527754 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3105. Min Act: -0.0000

Data Index: 98540 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3357. Min Act: -0.0000

Data Index: 994312 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1707466 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3212. Min Act: -0.0000

Data Index: 405558 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1906084 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1528359 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3296. Min Act: -0.0000

Data Index: 591959 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2847. Min Act: -0.0000

Data Index: 897201 (The Pile)

Max Activating Token Index: 535