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

Dataset: The Pile

Neuron 2547 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: 1.8660. Min Range: -1.8660

Max Act: 1.8552. Min Act: -0.0000

Data Index: 1494155 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8660. Min Act: -0.0000

Data Index: 1730218 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8586. Min Act: -0.0000

Data Index: 1613811 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6837. Min Act: -0.0000

Data Index: 1361493 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7859. Min Act: -0.0000

Data Index: 1438944 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6789. Min Act: -0.0000

Data Index: 740908 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6537. Min Act: -0.0000

Data Index: 1762745 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6298. Min Act: -0.0000

Data Index: 1818387 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1538851 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6009. Min Act: -0.0000

Data Index: 616399 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5576. Min Act: -0.0000

Data Index: 590271 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.4702. Min Act: -0.0000

Data Index: 825156 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5511. Min Act: -0.0000

Data Index: 864271 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5185. Min Act: -0.0000

Data Index: 788606 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5275. Min Act: -0.0000

Data Index: 902132 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5277. Min Act: -0.0000

Data Index: 315963 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6103. Min Act: -0.0000

Data Index: 1514634 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.4171. Min Act: -0.0000

Data Index: 655141 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.4979. Min Act: -0.0000

Data Index: 106259 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.4900. Min Act: -0.0000

Data Index: 907331 (The Pile)

Max Activating Token Index: 589