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

Dataset: The Pile

Neuron 2502 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: 0.3971. Min Range: -0.3971

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1516594 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1188939 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2606. Min Act: -0.0000

Data Index: 851507 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2681. Min Act: -0.0000

Data Index: 975670 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2700. Min Act: -0.0000

Data Index: 734354 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1104313 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2603. Min Act: -0.0000

Data Index: 68167 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1567498 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1551846 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2432. Min Act: -0.0000

Data Index: 452225 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2382. Min Act: -0.0000

Data Index: 445290 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1939044 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2358. Min Act: -0.0000

Data Index: 793282 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2643. Min Act: -0.0000

Data Index: 869065 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1411316 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1014772 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2134. Min Act: -0.0000

Data Index: 205642 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1940655 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1202338 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1682558 (The Pile)

Max Activating Token Index: 741