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

Dataset: The Pile

Neuron 3999 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: 0.5452. Min Range: -0.5452

Max Act: 0.5213. Min Act: -0.0000

Data Index: 490440 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4784. Min Act: -0.0000

Data Index: 425186 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4503. Min Act: -0.0000

Data Index: 949472 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4525. Min Act: -0.0000

Data Index: 818570 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4689. Min Act: -0.0000

Data Index: 510468 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1354919 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4523. Min Act: -0.0000

Data Index: 999401 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4572. Min Act: -0.0000

Data Index: 303026 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1823022 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1945046 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1213648 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1561940 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1048293 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4371. Min Act: -0.0000

Data Index: 903606 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4371. Min Act: -0.0000

Data Index: 381370 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1318580 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4394. Min Act: -0.0000

Data Index: 411134 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1834585 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3882. Min Act: -0.0000

Data Index: 322201 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4658. Min Act: -0.0000

Data Index: 474893 (The Pile)

Max Activating Token Index: 782