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

Dataset: The Pile

Neuron 3485 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.7526. Min Act: -0.0000

Data Index: 441504 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.4727. Min Act: -0.0000

Data Index: 709603 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1945993 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.2215. Min Act: -0.0000

Data Index: 296203 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1331460 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.7526. Min Range: -1.7526

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1597181 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9891. Min Act: -0.0000

Data Index: 627606 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9238. Min Act: -0.0000

Data Index: 529561 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9136. Min Act: -0.0000

Data Index: 212870 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1994697 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1610207 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9371. Min Act: -0.0000

Data Index: 474577 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1567972 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8799. Min Act: -0.0000

Data Index: 340984 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8757. Min Act: -0.0000

Data Index: 850045 (The Pile)

Max Activating Token Index: 978

Text #15

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8368. Min Act: 0.0000

Data Index: 1869998 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8862. Min Act: 0.0001

Data Index: 1294370 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1872839 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1966312 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 1.7526. Min Range: -1.7526

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1920819 (The Pile)

Max Activating Token Index: 263