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

Dataset: The Pile

Neuron 3681 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.7944. Min Act: -0.0000

Data Index: 1151135 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1669830 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.5212. Min Act: -0.0000

Data Index: 1231427 (The Pile)

Max Activating Token Index: 6

Text #3

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1761069 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1326031 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4987. Min Act: -0.0000

Data Index: 1116412 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4352. Min Act: -0.0000

Data Index: 110754 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1308995 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4550. Min Act: -0.0000

Data Index: 913166 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3611. Min Act: -0.0000

Data Index: 16662 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3964. Min Act: -0.0000

Data Index: 496656 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3902. Min Act: -0.0000

Data Index: 252431 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4229. Min Act: -0.0000

Data Index: 956215 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3669. Min Act: -0.0000

Data Index: 539710 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1887814 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1824775 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1552275 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.3400. Min Act: -0.0000

Data Index: 430104 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4965. Min Act: -0.0000

Data Index: 958858 (The Pile)

Max Activating Token Index: 5

Text #19

Max Range: 1.7944. Min Range: -1.7944

Max Act: 1.4965. Min Act: -0.0000

Data Index: 322086 (The Pile)

Max Activating Token Index: 5