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

Dataset: The Pile

Neuron 110 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0238. Min Range: -1.0238

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1172222 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1430031 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1047661 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1742544 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.6468. Min Act: -0.0000

Data Index: 136744 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1792343 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5785. Min Act: -0.0000

Data Index: 570285 (The Pile)

Max Activating Token Index: 541

Text #7

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1931389 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5360. Min Act: -0.0000

Data Index: 310920 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5051. Min Act: -0.0000

Data Index: 546528 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1083495 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1751370 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4909. Min Act: -0.0000

Data Index: 433660 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1364551 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4943. Min Act: -0.0000

Data Index: 730673 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1276198 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1540749 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4725. Min Act: -0.0000

Data Index: 174800 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1301423 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 1.0238. Min Range: -1.0238

Max Act: 0.4675. Min Act: -0.0000

Data Index: 423718 (The Pile)

Max Activating Token Index: 609