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

Dataset: The Pile

Neuron 2789 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: 1.3708. Min Range: -1.3708

Max Act: 1.3708. Min Act: -0.0000

Data Index: 510152 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1546481 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8194. Min Act: -0.0000

Data Index: 574484 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1453408 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1371475 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1328347 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1117103 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9894. Min Act: -0.0000

Data Index: 606371 (The Pile)

Max Activating Token Index: 520

Text #8

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1589149 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1631284 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8677. Min Act: -0.0000

Data Index: 60935 (The Pile)

Max Activating Token Index: 381

Text #11

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1344214 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8595. Min Act: -0.0000

Data Index: 760671 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1294448 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.7938. Min Act: -0.0000

Data Index: 506441 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8452. Min Act: -0.0000

Data Index: 315672 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.8175. Min Act: -0.0000

Data Index: 345226 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.7383. Min Act: -0.0000

Data Index: 53660 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9060. Min Act: -0.0000

Data Index: 147065 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1044575 (The Pile)

Max Activating Token Index: 902