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

Dataset: The Pile

Neuron 315 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.7076. Min Act: -0.0000

Data Index: 507226 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6357. Min Act: -0.0000

Data Index: 23879 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1860300 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1424249 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.6755. Min Act: -0.0000

Data Index: 12192 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4825. Min Act: -0.0000

Data Index: 482196 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1093890 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4601. Min Act: -0.0000

Data Index: 469138 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1264265 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1286352 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1484759 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1729759 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1392755 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4692. Min Act: -0.0000

Data Index: 177046 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4319. Min Act: -0.0000

Data Index: 636509 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1953205 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1002552 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1957080 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.4225. Min Act: -0.0000

Data Index: 439071 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.7076. Min Range: -0.7076

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1486065 (The Pile)

Max Activating Token Index: 276