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

Dataset: The Pile

Neuron 838 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1004225 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1517828 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1838797 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1970690 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1026824 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1789968 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2428. Min Act: -0.0000

Data Index: 939260 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1257157 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2414. Min Act: -0.0000

Data Index: 429619 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1742674 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2066. Min Act: -0.0000

Data Index: 75939 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.1840. Min Act: -0.0000

Data Index: 211358 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2036. Min Act: -0.0000

Data Index: 611249 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.1950. Min Act: -0.0000

Data Index: 545425 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2079. Min Act: -0.0000

Data Index: 311964 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2115. Min Act: -0.0000

Data Index: 140818 (The Pile)

Max Activating Token Index: 810

Text #16

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1850429 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1188696 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1841917 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 0.3671. Min Range: -0.3671

Max Act: 0.2104. Min Act: -0.0000

Data Index: 495758 (The Pile)

Max Activating Token Index: 746