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

Dataset: The Pile

Neuron 2569 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: 0.5807. Min Range: -0.5807

Max Act: 0.5807. Min Act: -0.0000

Data Index: 160302 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1085597 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4929. Min Act: -0.0000

Data Index: 675175 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5131. Min Act: -0.0000

Data Index: 120022 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4883. Min Act: -0.0000

Data Index: 365900 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1713004 (The Pile)

Max Activating Token Index: 309

Text #6

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4871. Min Act: -0.0000

Data Index: 269987 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1663697 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4384. Min Act: -0.0000

Data Index: 181565 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1737246 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4594. Min Act: -0.0000

Data Index: 595567 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4258. Min Act: -0.0000

Data Index: 747964 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4265. Min Act: -0.0000

Data Index: 515018 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1317994 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1220004 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1203777 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4054. Min Act: -0.0000

Data Index: 619516 (The Pile)

Max Activating Token Index: 927

Text #17

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4426. Min Act: -0.0000

Data Index: 206052 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1042024 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1676556 (The Pile)

Max Activating Token Index: 771