Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2945 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.6144. Min Act: -0.0000

Data Index: 1630246 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.5567. Min Act: -0.0000

Data Index: 1544200 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1943037 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1277329 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.4959. Min Act: -0.0000

Data Index: 1877582 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.5364. Min Act: -0.0000

Data Index: 584898 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1535984 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.5453. Min Act: -0.0000

Data Index: 877299 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1070372 (The Pile)

Max Activating Token Index: 79

Text #9

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.3138. Min Act: -0.0000

Data Index: 1011850 (The Pile)

Max Activating Token Index: 783

Text #10

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.3692. Min Act: -0.0000

Data Index: 75221 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1455506 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.2805. Min Act: -0.0000

Data Index: 992950 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.4159. Min Act: -0.0000

Data Index: 739999 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.2594. Min Act: -0.0000

Data Index: 770419 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.3223. Min Act: -0.0000

Data Index: 507227 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1126139 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.3969. Min Act: -0.0000

Data Index: 848405 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1087207 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.6333. Min Range: -1.6333

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1156437 (The Pile)

Max Activating Token Index: 39