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

Dataset: The Pile

Neuron 4906 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.5328. Min Act: 0.0000

Data Index: 1613458 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3954. Min Act: -0.0000

Data Index: 1595601 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1956692 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.1066. Min Act: -0.0000

Data Index: 198001 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.0633. Min Act: -0.0000

Data Index: 962224 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9882. Min Act: -0.0000

Data Index: 1070823 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8968. Min Act: -0.0000

Data Index: 476636 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1462687 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8883. Min Act: -0.0000

Data Index: 694076 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9572. Min Act: -0.0000

Data Index: 841308 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8985. Min Act: 0.0000

Data Index: 387184 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9553. Min Act: -0.0000

Data Index: 700119 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8945. Min Act: -0.0000

Data Index: 129622 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1889326 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1613809 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1399740 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8901. Min Act: -0.0000

Data Index: 116019 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.8901. Min Act: 0.0000

Data Index: 903961 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1129406 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 1.5328. Min Range: -1.5328

Max Act: 0.9385. Min Act: -0.0000

Data Index: 491855 (The Pile)

Max Activating Token Index: 685