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

Dataset: The Pile

Neuron 2724 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: 5.4789. Min Range: -5.4789

Max Act: 5.4581. Min Act: -0.0000

Data Index: 639935 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.8758. Min Act: -0.0000

Data Index: 483617 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.6882. Min Act: -0.0000

Data Index: 944314 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 5.4789. Min Range: -5.4789

Max Act: 5.1498. Min Act: -0.0000

Data Index: 250631 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.8268. Min Act: -0.0000

Data Index: 1602472 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.9685. Min Act: -0.0000

Data Index: 1454937 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 5.4789. Min Range: -5.4789

Max Act: 5.0286. Min Act: -0.0000

Data Index: 52518 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 5.4789. Min Range: -5.4789

Max Act: 5.1350. Min Act: -0.0000

Data Index: 1723197 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.7057. Min Act: -0.0000

Data Index: 878158 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 5.4789. Min Range: -5.4789

Max Act: 5.4789. Min Act: -0.0000

Data Index: 137121 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.3266. Min Act: -0.0000

Data Index: 818528 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.8431. Min Act: -0.0000

Data Index: 152156 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.8404. Min Act: -0.0000

Data Index: 906405 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 5.4789. Min Range: -5.4789

Max Act: 3.9675. Min Act: -0.0000

Data Index: 1360211 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 5.4789. Min Range: -5.4789

Max Act: 3.9675. Min Act: -0.0000

Data Index: 899915 (The Pile)

Max Activating Token Index: 44

Text #15

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.9348. Min Act: -0.0000

Data Index: 620512 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.9619. Min Act: -0.0000

Data Index: 1808050 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.5475. Min Act: -0.0000

Data Index: 599458 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.2740. Min Act: -0.0000

Data Index: 1080141 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 5.4789. Min Range: -5.4789

Max Act: 4.6264. Min Act: -0.0000

Data Index: 1413656 (The Pile)

Max Activating Token Index: 281