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

Dataset: The Pile

Neuron 4439 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7301. Min Act: -0.0000

Data Index: 762534 (The Pile)

Max Activating Token Index: 965

Text #1

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7052. Min Act: -0.0000

Data Index: 871216 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5990. Min Act: -0.0000

Data Index: 890489 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6708. Min Act: -0.0000

Data Index: 259615 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5749. Min Act: -0.0000

Data Index: 1377059 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5781. Min Act: -0.0000

Data Index: 1617534 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5387. Min Act: -0.0000

Data Index: 451048 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7615. Min Act: -0.0000

Data Index: 105383 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1128018 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5141. Min Act: -0.0000

Data Index: 1624341 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1540329 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1624474 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1004294 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1829713 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2510. Min Act: -0.0000

Data Index: 253695 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3574. Min Act: -0.0000

Data Index: 895241 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4130. Min Act: -0.0000

Data Index: 84944 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4141. Min Act: -0.0000

Data Index: 191731 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1223059 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.0916. Min Act: -0.0000

Data Index: 795448 (The Pile)

Max Activating Token Index: 854