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

Dataset: The Pile

Neuron 2288 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: 0.7404. Min Range: -0.7404

Max Act: 0.7404. Min Act: -0.0000

Data Index: 983613 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1993405 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1904070 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6672. Min Act: -0.0000

Data Index: 957672 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6697. Min Act: -0.0000

Data Index: 995696 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1350917 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1731671 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6510. Min Act: -0.0000

Data Index: 966191 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5969. Min Act: -0.0000

Data Index: 393535 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5705. Min Act: -0.0000

Data Index: 305456 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.6022. Min Act: -0.0000

Data Index: 213686 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1735155 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5737. Min Act: -0.0000

Data Index: 944437 (The Pile)

Max Activating Token Index: 187

Text #13

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1410038 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1152420 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1458112 (The Pile)

Max Activating Token Index: 197

Text #16

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5718. Min Act: -0.0000

Data Index: 398410 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1003221 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5632. Min Act: -0.0000

Data Index: 861291 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.7404. Min Range: -0.7404

Max Act: 0.5528. Min Act: -0.0000

Data Index: 816097 (The Pile)

Max Activating Token Index: 451