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

Dataset: The Pile

Neuron 736 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: 0.3522. Min Range: -0.3522

Max Act: 0.3522. Min Act: -0.0000

Data Index: 577204 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3051. Min Act: -0.0000

Data Index: 773876 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1630373 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1768074 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2751. Min Act: -0.0000

Data Index: 801898 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1205029 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1665105 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1668802 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2519. Min Act: -0.0000

Data Index: 35730 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2592. Min Act: -0.0000

Data Index: 196408 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2410. Min Act: -0.0000

Data Index: 627889 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1123395 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1186820 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2726. Min Act: -0.0000

Data Index: 975117 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2575. Min Act: -0.0000

Data Index: 940634 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1471167 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1620553 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2324. Min Act: -0.0000

Data Index: 332648 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2485. Min Act: -0.0000

Data Index: 162105 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.3522. Min Range: -0.3522

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1029704 (The Pile)

Max Activating Token Index: 84