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

Dataset: The Pile

Neuron 3362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1730032 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1485033 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1524466 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4856. Min Act: -0.0000

Data Index: 790842 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4675. Min Act: -0.0000

Data Index: 778869 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4454. Min Act: -0.0000

Data Index: 631057 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1607297 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1829864 (The Pile)

Max Activating Token Index: 209

Text #8

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1100387 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1427474 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4550. Min Act: -0.0000

Data Index: 455609 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4830. Min Act: -0.0000

Data Index: 220873 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4262. Min Act: -0.0000

Data Index: 433305 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1949365 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4223. Min Act: -0.0000

Data Index: 858228 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1753056 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1052925 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1653323 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4196. Min Act: -0.0000

Data Index: 274363 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1958062 (The Pile)

Max Activating Token Index: 686