Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.6478. Min Act: -0.0000

Data Index: 681247 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.6276. Min Act: -0.0000

Data Index: 802697 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5696. Min Act: -0.0000

Data Index: 985923 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.6426. Min Act: -0.0000

Data Index: 632283 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5664. Min Act: -0.0000

Data Index: 834 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5213. Min Act: -0.0000

Data Index: 418487 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4997. Min Act: -0.0000

Data Index: 180008 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1608728 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1226375 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4827. Min Act: -0.0000

Data Index: 338497 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1676798 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4480. Min Act: -0.0000

Data Index: 618594 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4758. Min Act: -0.0000

Data Index: 692885 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1959610 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4144. Min Act: -0.0000

Data Index: 626198 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1612360 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1183389 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1338427 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1637572 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4694. Min Act: -0.0000

Data Index: 347490 (The Pile)

Max Activating Token Index: 844