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

Dataset: The Pile

Neuron 3917 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6660. Min Act: -0.0000

Data Index: 368253 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1758503 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1235945 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4889. Min Act: -0.0000

Data Index: 822743 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4770. Min Act: -0.0000

Data Index: 996464 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4489. Min Act: -0.0000

Data Index: 114630 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4547. Min Act: -0.0000

Data Index: 135148 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1515287 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1232304 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4415. Min Act: 0.0000

Data Index: 1493820 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4018. Min Act: -0.0000

Data Index: 540362 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1606271 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4271. Min Act: -0.0000

Data Index: 612040 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1130517 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4332. Min Act: -0.0000

Data Index: 526522 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4261. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 342