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

Dataset: The Pile

Neuron 2595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1360. Min Range: -5.1360

Max Act: 5.1360. Min Act: -0.0000

Data Index: 1443026 (The Pile)

Max Activating Token Index: 741

Text #1

Max Range: 5.1360. Min Range: -5.1360

Max Act: 5.0592. Min Act: -0.0000

Data Index: 1228219 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 5.1360. Min Range: -5.1360

Max Act: 5.0348. Min Act: -0.0000

Data Index: 647219 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.6152. Min Act: -0.0000

Data Index: 1019060 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.6834. Min Act: -0.0000

Data Index: 1195613 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.8144. Min Act: -0.0000

Data Index: 1091866 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.8780. Min Act: -0.0000

Data Index: 1233857 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.8947. Min Act: -0.0000

Data Index: 1451747 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.7079. Min Act: -0.0000

Data Index: 1950027 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.6220. Min Act: -0.0000

Data Index: 44897 (The Pile)

Max Activating Token Index: 965

Text #10

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.5818. Min Act: -0.0000

Data Index: 1229391 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.5544. Min Act: -0.0000

Data Index: 1223747 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.4936. Min Act: -0.0000

Data Index: 302887 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.6003. Min Act: -0.0000

Data Index: 1326120 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.3485. Min Act: -0.0000

Data Index: 504470 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.1737. Min Act: -0.0000

Data Index: 1791112 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.1707. Min Act: -0.0000

Data Index: 1916503 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.3366. Min Act: -0.0000

Data Index: 1798163 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.4530. Min Act: -0.0000

Data Index: 1414410 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 5.1360. Min Range: -5.1360

Max Act: 4.2686. Min Act: -0.0000

Data Index: 1282094 (The Pile)

Max Activating Token Index: 353