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

Dataset: The Pile

Neuron 2955 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: 1.4904. Min Range: -1.4904

Max Act: 1.4904. Min Act: -0.0000

Data Index: 337518 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.0415. Min Act: -0.0000

Data Index: 57440 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.2796. Min Act: -0.0000

Data Index: 538923 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1298501 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.2921. Min Act: -0.0000

Data Index: 595083 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.2320. Min Act: -0.0000

Data Index: 652176 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.0040. Min Act: -0.0000

Data Index: 678850 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.9708. Min Act: -0.0000

Data Index: 175867 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1395421 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1513951 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.9677. Min Act: -0.0000

Data Index: 812720 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.9338. Min Act: -0.0000

Data Index: 426570 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1926268 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1424284 (The Pile)

Max Activating Token Index: 79

Text #14

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.8338. Min Act: -0.0000

Data Index: 305293 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1501435 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.8872. Min Act: -0.0000

Data Index: 587693 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1166851 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1694472 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1416501 (The Pile)

Max Activating Token Index: 872