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

Dataset: The Pile

Neuron 4509 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: 0.5598. Min Range: -0.5598

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1763758 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1306294 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1142394 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1445130 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4419. Min Act: -0.0000

Data Index: 655995 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1490398 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4407. Min Act: -0.0000

Data Index: 833703 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1927196 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1065397 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4320. Min Act: -0.0000

Data Index: 723730 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1581508 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4052. Min Act: -0.0000

Data Index: 538676 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4259. Min Act: -0.0000

Data Index: 288564 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4248. Min Act: -0.0000

Data Index: 186668 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1898854 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1114828 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1433756 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1638467 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.3958. Min Act: -0.0000

Data Index: 188096 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.5598. Min Range: -0.5598

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1162374 (The Pile)

Max Activating Token Index: 472