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

Dataset: The Pile

Neuron 3787 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1447052 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6340. Min Act: -0.0000

Data Index: 167812 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6286. Min Act: -0.0000

Data Index: 1989742 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6328. Min Act: -0.0000

Data Index: 927413 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1446985 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3552. Min Act: -0.0000

Data Index: 997390 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1375160 (The Pile)

Max Activating Token Index: 600

Text #7

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2008. Min Act: -0.0000

Data Index: 69047 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2946. Min Act: -0.0000

Data Index: 329935 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1361255 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1223524 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.1845. Min Act: -0.0000

Data Index: 706223 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1287984 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.1393. Min Act: -0.0000

Data Index: 303188 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1440450 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.1024. Min Act: -0.0000

Data Index: 511298 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.0918. Min Act: -0.0000

Data Index: 934650 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.0461. Min Act: -0.0000

Data Index: 807231 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1135111 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1076792 (The Pile)

Max Activating Token Index: 332