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

Dataset: The Pile

Neuron 4983 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: 0.9225. Min Range: -0.9225

Max Act: 0.8296. Min Act: -0.0000

Data Index: 755442 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.9225. Min Act: -0.0000

Data Index: 928332 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.9143. Min Act: -0.0000

Data Index: 2350 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1136419 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.8138. Min Act: -0.0000

Data Index: 418069 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.8876. Min Act: -0.0000

Data Index: 67612 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7767. Min Act: -0.0000

Data Index: 955656 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1005598 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7895. Min Act: -0.0000

Data Index: 628998 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1233446 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7484. Min Act: -0.0000

Data Index: 739731 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7713. Min Act: -0.0000

Data Index: 696787 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1218929 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1413185 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7482. Min Act: -0.0000

Data Index: 847197 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.6719. Min Act: -0.0000

Data Index: 638868 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1634574 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1626145 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.6924. Min Act: -0.0000

Data Index: 718192 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.9225. Min Range: -0.9225

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1707450 (The Pile)

Max Activating Token Index: 810