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

Dataset: The Pile

Neuron 457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.5040. Min Act: -0.0000

Data Index: 253311 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.2651. Min Act: -0.0000

Data Index: 783128 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.2414. Min Act: -0.0000

Data Index: 180290 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1641521 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1303. Min Act: -0.0000

Data Index: 364573 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1292. Min Act: -0.0000

Data Index: 752644 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0916. Min Act: -0.0000

Data Index: 625950 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1887576 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1710443 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1031187 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0845. Min Act: -0.0000

Data Index: 27213 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1530076 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0875. Min Act: -0.0000

Data Index: 407028 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1464381 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0378. Min Act: -0.0000

Data Index: 600499 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1684707 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0279. Min Act: -0.0000

Data Index: 19792 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0299. Min Act: -0.0000

Data Index: 409499 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.5040. Min Range: -1.5040

Max Act: 1.0214. Min Act: -0.0000

Data Index: 913651 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.5040. Min Range: -1.5040

Max Act: 0.9907. Min Act: -0.0000

Data Index: 119987 (The Pile)

Max Activating Token Index: 598