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

Dataset: The Pile

Neuron 3917 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2660. Min Range: -5.2660

Max Act: 5.2660. Min Act: -0.0000

Data Index: 28042 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.8453. Min Act: -0.0000

Data Index: 1690546 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.6116. Min Act: -0.0000

Data Index: 1205935 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.9581. Min Act: -0.0000

Data Index: 351666 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.3669. Min Act: -0.0000

Data Index: 1921864 (The Pile)

Max Activating Token Index: 303

Text #5

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.6890. Min Act: -0.0000

Data Index: 1785830 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.2061. Min Act: -0.0000

Data Index: 1149628 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.1929. Min Act: -0.0000

Data Index: 965844 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.3181. Min Act: -0.0000

Data Index: 372372 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.1575. Min Act: -0.0000

Data Index: 714654 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.1936. Min Act: -0.0001

Data Index: 853183 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.2500. Min Act: -0.0000

Data Index: 1298673 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.3774. Min Act: -0.0000

Data Index: 1540578 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.4082. Min Act: -0.0000

Data Index: 853652 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.1988. Min Act: -0.0000

Data Index: 375934 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.9484. Min Act: -0.0000

Data Index: 744319 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 5.2660. Min Range: -5.2660

Max Act: 3.9555. Min Act: -0.0000

Data Index: 1512029 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.0289. Min Act: -0.0000

Data Index: 1858931 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.3512. Min Act: -0.0000

Data Index: 1790738 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 5.2660. Min Range: -5.2660

Max Act: 4.0070. Min Act: -0.0000

Data Index: 173225 (The Pile)

Max Activating Token Index: 159