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

Dataset: The Pile

Neuron 5012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.8168. Min Act: -0.0000

Data Index: 1679037 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.4083. Min Act: -0.0000

Data Index: 920752 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.1687. Min Act: -0.0000

Data Index: 513085 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1169843 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.0061. Min Act: -0.0000

Data Index: 181749 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.9130. Min Act: -0.0000

Data Index: 774246 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1062574 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.8066. Min Act: -0.0000

Data Index: 336061 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.8305. Min Act: -0.0000

Data Index: 766536 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1929957 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1809297 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1610650 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.6949. Min Act: -0.0000

Data Index: 462132 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.6967. Min Act: -0.0000

Data Index: 402009 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.7041. Min Act: -0.0000

Data Index: 77914 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.7066. Min Act: -0.0000

Data Index: 526313 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1916038 (The Pile)

Max Activating Token Index: 97

Text #17

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1663236 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1195961 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.8168. Min Range: -1.8168

Max Act: 0.6258. Min Act: -0.0000

Data Index: 968116 (The Pile)

Max Activating Token Index: 622