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

Dataset: The Pile

Neuron 2394 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.7591. Min Act: -0.0000

Data Index: 566183 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.7142. Min Act: -0.0000

Data Index: 762544 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1617324 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6489. Min Act: -0.0000

Data Index: 820194 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6938. Min Act: -0.0000

Data Index: 526033 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1268877 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1061689 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1115656 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1744470 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1970771 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5964. Min Act: -0.0000

Data Index: 218947 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1736170 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1053523 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1236291 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5738. Min Act: -0.0000

Data Index: 607709 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5654. Min Act: -0.0000

Data Index: 584881 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5786. Min Act: -0.0000

Data Index: 662437 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5593. Min Act: 0.0000

Data Index: 1382132 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5487. Min Act: -0.0000

Data Index: 134568 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5376. Min Act: -0.0000

Data Index: 503272 (The Pile)

Max Activating Token Index: 533