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

Dataset: The Pile

Neuron 3679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.9181. Min Act: -0.0000

Data Index: 607874 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8724. Min Act: -0.0000

Data Index: 504879 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.9048. Min Act: -0.0000

Data Index: 612083 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1824281 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1462220 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8712. Min Act: -0.0000

Data Index: 642392 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8246. Min Act: -0.0000

Data Index: 410754 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8228. Min Act: 0.0000

Data Index: 1843110 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1242428 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7887. Min Act: -0.0000

Data Index: 463033 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7401. Min Act: -0.0000

Data Index: 513034 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1901626 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7177. Min Act: -0.0000

Data Index: 430863 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1841983 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1055161 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.6391. Min Act: -0.0000

Data Index: 721942 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7174. Min Act: -0.0000

Data Index: 943014 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7351. Min Act: -0.0000

Data Index: 848824 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7168. Min Act: -0.0000

Data Index: 389156 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.9181. Min Range: -0.9181

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1466737 (The Pile)

Max Activating Token Index: 372