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

Dataset: The Pile

Neuron 3214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7932. Min Act: -0.0000

Data Index: 761269 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.7172. Min Act: -0.0000

Data Index: 712750 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1734118 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1803929 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1345216 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1862030 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5896. Min Act: -0.0000

Data Index: 276073 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6304. Min Act: -0.0000

Data Index: 789172 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1617314 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6374. Min Act: -0.0000

Data Index: 200345 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1286129 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1639789 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1107725 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5768. Min Act: -0.0000

Data Index: 822704 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1036003 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5640. Min Act: -0.0000

Data Index: 521056 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5774. Min Act: -0.0000

Data Index: 682738 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5783. Min Act: -0.0000

Data Index: 477487 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.6000. Min Act: -0.0000

Data Index: 929874 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 0.7932. Min Range: -0.7932

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1556176 (The Pile)

Max Activating Token Index: 578