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

Dataset: The Pile

Neuron 3513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.9858. Min Act: -0.0000

Data Index: 508583 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.9765. Min Act: -0.0000

Data Index: 1800013 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.9252. Min Act: -0.0000

Data Index: 676455 (The Pile)

Max Activating Token Index: 45

Text #3

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.9396. Min Act: -0.0000

Data Index: 1214675 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.8337. Min Act: -0.0000

Data Index: 1631790 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.6317. Min Act: -0.0000

Data Index: 412365 (The Pile)

Max Activating Token Index: 68

Text #6

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.5559. Min Act: -0.0000

Data Index: 300949 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.3969. Min Act: -0.0000

Data Index: 1974603 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.2221. Min Act: -0.0000

Data Index: 769858 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.2603. Min Act: -0.0000

Data Index: 1109804 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.1523. Min Act: -0.0000

Data Index: 140544 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.1289. Min Act: -0.0000

Data Index: 671091 (The Pile)

Max Activating Token Index: 84

Text #12

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.1376. Min Act: -0.0000

Data Index: 1093417 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.1102. Min Act: -0.0000

Data Index: 1221319 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.0976. Min Act: -0.0000

Data Index: 631626 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.0964. Min Act: -0.0000

Data Index: 1575038 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.0649. Min Act: -0.0000

Data Index: 1252259 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 5.9858. Min Range: -5.9858

Max Act: 4.8271. Min Act: -0.0000

Data Index: 1969942 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 5.9858. Min Range: -5.9858

Max Act: 5.1535. Min Act: -0.0000

Data Index: 1114268 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 5.9858. Min Range: -5.9858

Max Act: 4.9877. Min Act: -0.0000

Data Index: 266241 (The Pile)

Max Activating Token Index: 61