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

Dataset: The Pile

Neuron 4822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.6294. Min Act: -0.0000

Data Index: 90167 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4634. Min Act: -0.0000

Data Index: 776650 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1681185 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.5754. Min Act: -0.0000

Data Index: 951637 (The Pile)

Max Activating Token Index: 659

Text #4

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.5549. Min Act: -0.0000

Data Index: 940719 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1145311 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4841. Min Act: -0.0000

Data Index: 834560 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.5221. Min Act: -0.0000

Data Index: 953362 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4768. Min Act: -0.0000

Data Index: 222071 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4633. Min Act: -0.0000

Data Index: 615123 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1242292 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4988. Min Act: -0.0000

Data Index: 62100 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4965. Min Act: -0.0000

Data Index: 862419 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1297203 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4956. Min Act: -0.0000

Data Index: 750779 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4711. Min Act: -0.0000

Data Index: 310863 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1115906 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4852. Min Act: -0.0000

Data Index: 616435 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1612881 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.6294. Min Range: -0.6294

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1480506 (The Pile)

Max Activating Token Index: 796