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

Dataset: The Pile

Neuron 3334 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: 0.9581. Min Range: -0.9581

Max Act: 0.9581. Min Act: -0.0000

Data Index: 371266 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1052072 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1367192 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8015. Min Act: -0.0000

Data Index: 715803 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8648. Min Act: -0.0000

Data Index: 92009 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1644944 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8463. Min Act: -0.0000

Data Index: 161047 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1797508 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8359. Min Act: -0.0000

Data Index: 240821 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8280. Min Act: -0.0000

Data Index: 9193 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1826419 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1880779 (The Pile)

Max Activating Token Index: 319

Text #12

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1419753 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7348. Min Act: -0.0000

Data Index: 309077 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1003986 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1756063 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7782. Min Act: -0.0000

Data Index: 872311 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7465. Min Act: -0.0000

Data Index: 568116 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7725. Min Act: -0.0000

Data Index: 940145 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.9581. Min Range: -0.9581

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1255261 (The Pile)

Max Activating Token Index: 257