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

Dataset: The Pile

Neuron 943 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: 0.9652. Min Range: -0.9652

Max Act: 0.9652. Min Act: -0.0000

Data Index: 1558282 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1478087 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8863. Min Act: -0.0000

Data Index: 513447 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1253150 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1135444 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8324. Min Act: -0.0000

Data Index: 608757 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8947. Min Act: -0.0000

Data Index: 561355 (The Pile)

Max Activating Token Index: 898

Text #7

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7426. Min Act: -0.0000

Data Index: 192548 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7214. Min Act: -0.0000

Data Index: 721609 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8492. Min Act: -0.0000

Data Index: 766330 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1055737 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1740737 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8018. Min Act: -0.0000

Data Index: 94753 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7362. Min Act: -0.0000

Data Index: 947135 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7570. Min Act: -0.0000

Data Index: 800159 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1985327 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7666. Min Act: -0.0000

Data Index: 440883 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1863447 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1636655 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1055416 (The Pile)

Max Activating Token Index: 1000