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

Dataset: The Pile

Neuron 790 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: 3.3429. Min Range: -3.3429

Max Act: 3.2567. Min Act: -0.0000

Data Index: 1157311 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 3.3429. Min Range: -3.3429

Max Act: 3.3429. Min Act: -0.0000

Data Index: 692416 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 3.3429. Min Range: -3.3429

Max Act: 3.1657. Min Act: -0.0000

Data Index: 916766 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.8349. Min Act: -0.0000

Data Index: 1090748 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 3.3429. Min Range: -3.3429

Max Act: 3.0981. Min Act: -0.0000

Data Index: 678091 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 3.3429. Min Range: -3.3429

Max Act: 3.2108. Min Act: -0.0000

Data Index: 1241000 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 3.3429. Min Range: -3.3429

Max Act: 3.1534. Min Act: -0.0000

Data Index: 1723777 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 3.3429. Min Range: -3.3429

Max Act: 3.0619. Min Act: -0.0000

Data Index: 1688077 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1578043 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.8996. Min Act: -0.0000

Data Index: 5768 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.6585. Min Act: -0.0000

Data Index: 308810 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.6601. Min Act: -0.0000

Data Index: 630497 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.8795. Min Act: -0.0000

Data Index: 135527 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.6080. Min Act: -0.0000

Data Index: 1511641 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.4467. Min Act: -0.0000

Data Index: 1487435 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.4064. Min Act: -0.0000

Data Index: 227817 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.4612. Min Act: -0.0000

Data Index: 1563269 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.4408. Min Act: -0.0000

Data Index: 1802718 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.5783. Min Act: -0.0000

Data Index: 1273324 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 3.3429. Min Range: -3.3429

Max Act: 2.3084. Min Act: -0.0000

Data Index: 602162 (The Pile)

Max Activating Token Index: 924