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

Dataset: The Pile

Neuron 3271 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: 0.4388. Min Range: -0.4388

Max Act: 0.4388. Min Act: -0.0000

Data Index: 898183 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.4123. Min Act: -0.0000

Data Index: 686256 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1576916 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1824510 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3136. Min Act: -0.0000

Data Index: 358009 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1219345 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1431504 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1714878 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1490032 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1954023 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1149152 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2800. Min Act: -0.0000

Data Index: 581753 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1660215 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1118177 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2647. Min Act: -0.0000

Data Index: 275813 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2731. Min Act: -0.0000

Data Index: 356128 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2808. Min Act: -0.0000

Data Index: 168272 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1463093 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2598. Min Act: -0.0000

Data Index: 882724 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2636. Min Act: -0.0000

Data Index: 20795 (The Pile)

Max Activating Token Index: 710