Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 920 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1993. Min Range: -1.1993

Max Act: 1.1993. Min Act: -0.0000

Data Index: 853343 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9440. Min Act: -0.0000

Data Index: 954775 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1999569 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1832366 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1527830 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1749015 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8687. Min Act: -0.0001

Data Index: 1793149 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.7681. Min Act: -0.0001

Data Index: 418577 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8504. Min Act: -0.0000

Data Index: 717231 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8460. Min Act: -0.0000

Data Index: 260675 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8363. Min Act: -0.0001

Data Index: 241110 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.7646. Min Act: -0.0001

Data Index: 1148530 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1265874 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1564500 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8132. Min Act: -0.0001

Data Index: 1974624 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8360. Min Act: -0.0000

Data Index: 786139 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.7377. Min Act: -0.0001

Data Index: 1352053 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8188. Min Act: 0.0000

Data Index: 1103241 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.7915. Min Act: -0.0000

Data Index: 587859 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 1.1993. Min Range: -1.1993

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1362773 (The Pile)

Max Activating Token Index: 992