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

Dataset: The Pile

Neuron 2473 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: 0.4154. Min Range: -0.4154

Max Act: 0.4154. Min Act: -0.0000

Data Index: 838053 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1329158 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3692. Min Act: -0.0000

Data Index: 881601 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1038862 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3646. Min Act: -0.0000

Data Index: 692948 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3374. Min Act: -0.0000

Data Index: 47467 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3715. Min Act: -0.0000

Data Index: 832534 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3573. Min Act: -0.0000

Data Index: 517331 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3405. Min Act: -0.0000

Data Index: 456527 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3725. Min Act: -0.0000

Data Index: 723247 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1476849 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3423. Min Act: -0.0000

Data Index: 866285 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1515652 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3419. Min Act: -0.0000

Data Index: 266697 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1518527 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3182. Min Act: -0.0000

Data Index: 44098 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3375. Min Act: -0.0000

Data Index: 842119 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3462. Min Act: -0.0000

Data Index: 57677 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1530667 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1440491 (The Pile)

Max Activating Token Index: 111