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

Dataset: The Pile

Neuron 2033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1466360 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 1.0399. Min Range: -1.0399

Max Act: 1.0399. Min Act: -0.0000

Data Index: 814633 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.0399. Min Range: -1.0399

Max Act: 1.0302. Min Act: -0.0000

Data Index: 76922 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1215661 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9301. Min Act: -0.0000

Data Index: 211941 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9332. Min Act: -0.0000

Data Index: 871841 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8915. Min Act: -0.0000

Data Index: 847859 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.9328. Min Act: -0.0000

Data Index: 949737 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8681. Min Act: -0.0000

Data Index: 269866 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1968226 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1538287 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8021. Min Act: 0.0000

Data Index: 813412 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8999. Min Act: -0.0000

Data Index: 352915 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1295111 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1342579 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1816460 (The Pile)

Max Activating Token Index: 18

Text #16

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8378. Min Act: -0.0000

Data Index: 833070 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1073979 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8136. Min Act: -0.0000

Data Index: 558825 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 1.0399. Min Range: -1.0399

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1529036 (The Pile)

Max Activating Token Index: 140