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

Dataset: The Pile

Neuron 1284 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2771. Min Act: -0.0000

Data Index: 646568 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2716. Min Act: -0.0000

Data Index: 476529 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2694. Min Act: -0.0000

Data Index: 513691 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1610929 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2370. Min Act: -0.0000

Data Index: 273224 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2504. Min Act: -0.0000

Data Index: 838442 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2408. Min Act: -0.0000

Data Index: 851990 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1106999 (The Pile)

Max Activating Token Index: 556

Text #8

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2375. Min Act: -0.0000

Data Index: 813729 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2202. Min Act: -0.0000

Data Index: 854593 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2230. Min Act: 0.0000

Data Index: 264499 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1510655 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2108. Min Act: -0.0000

Data Index: 525879 (The Pile)

Max Activating Token Index: 398

Text #13

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1290164 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1586648 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1306851 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1625544 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1614589 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2033. Min Act: -0.0000

Data Index: 259843 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 0.2771. Min Range: -0.2771

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1990162 (The Pile)

Max Activating Token Index: 481