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

Dataset: The Pile

Neuron 4600 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: 1.2405. Min Range: -1.2405

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1390349 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.2249. Min Act: -0.0000

Data Index: 6361 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0996. Min Act: -0.0000

Data Index: 358717 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1244. Min Act: -0.0000

Data Index: 927792 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1736519 (The Pile)

Max Activating Token Index: 600

Text #5

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1100. Min Act: -0.0000

Data Index: 48500 (The Pile)

Max Activating Token Index: 773

Text #6

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1563334 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1476. Min Act: -0.0000

Data Index: 290159 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1725292 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1105228 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0467. Min Act: -0.0000

Data Index: 556253 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0946. Min Act: -0.0000

Data Index: 236154 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1855523 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9880. Min Act: -0.0000

Data Index: 764674 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9598. Min Act: -0.0000

Data Index: 711759 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 1.2405. Min Range: -1.2405

Max Act: 1.0097. Min Act: -0.0000

Data Index: 70996 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9793. Min Act: -0.0000

Data Index: 390515 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1720663 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9601. Min Act: -0.0000

Data Index: 582366 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 1.2405. Min Range: -1.2405

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1222791 (The Pile)

Max Activating Token Index: 815