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

Dataset: The Pile

Neuron 1910 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: 0.6388. Min Range: -0.6388

Max Act: 0.6178. Min Act: -0.0000

Data Index: 370552 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1121617 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6280. Min Act: -0.0000

Data Index: 358321 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6197. Min Act: -0.0000

Data Index: 97964 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5595. Min Act: -0.0000

Data Index: 687012 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1965874 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1664317 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5615. Min Act: -0.0000

Data Index: 714238 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1423865 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1036652 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5694. Min Act: -0.0000

Data Index: 771810 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1224345 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5695. Min Act: -0.0000

Data Index: 644859 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1080080 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1416348 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1801553 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1281004 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5090. Min Act: -0.0000

Data Index: 381719 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5431. Min Act: -0.0000

Data Index: 236744 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1646590 (The Pile)

Max Activating Token Index: 142