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

Dataset: The Pile

Neuron 4724 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: 1.3586. Min Range: -1.3586

Max Act: 1.3017. Min Act: -0.0000

Data Index: 197495 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.3586. Min Act: -0.0000

Data Index: 14701 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.0887. Min Act: -0.0000

Data Index: 790422 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.0153. Min Act: -0.0000

Data Index: 785167 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9055. Min Act: -0.0000

Data Index: 217955 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.1047. Min Act: -0.0000

Data Index: 768957 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.0198. Min Act: -0.0000

Data Index: 595876 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 1.3586. Min Range: -1.3586

Max Act: 1.0442. Min Act: -0.0000

Data Index: 230959 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9936. Min Act: -0.0000

Data Index: 997634 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9272. Min Act: -0.0000

Data Index: 392687 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9096. Min Act: -0.0000

Data Index: 610100 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8761. Min Act: -0.0000

Data Index: 82366 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9550. Min Act: -0.0000

Data Index: 299600 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.9204. Min Act: -0.0000

Data Index: 201860 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8145. Min Act: -0.0000

Data Index: 248451 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1416281 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1661911 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1771764 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1778926 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.3586. Min Range: -1.3586

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1439445 (The Pile)

Max Activating Token Index: 690