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

Dataset: The Pile

Neuron 399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8818. Min Act: -0.0000

Data Index: 948718 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9043. Min Act: -0.0000

Data Index: 621710 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1420498 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9650. Min Act: -0.0000

Data Index: 342606 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1588372 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1048801 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8601. Min Act: -0.0000

Data Index: 545004 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1010382 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8554. Min Act: -0.0000

Data Index: 633056 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9257. Min Act: -0.0000

Data Index: 677810 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8499. Min Act: -0.0000

Data Index: 953543 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8962. Min Act: -0.0000

Data Index: 301348 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8013. Min Act: -0.0000

Data Index: 449395 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8461. Min Act: -0.0000

Data Index: 723529 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1453704 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1273360 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1558401 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1900288 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.9034. Min Act: -0.0000

Data Index: 48708 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.9650. Min Range: -0.9650

Max Act: 0.8329. Min Act: -0.0000

Data Index: 109685 (The Pile)

Max Activating Token Index: 769