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

Dataset: The Pile

Neuron 1442 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.2501. Min Act: -0.0000

Data Index: 1684822 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.1951. Min Act: -0.0000

Data Index: 1618551 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.0304. Min Act: -0.0000

Data Index: 1379569 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.9651. Min Act: -0.0000

Data Index: 1387456 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.0260. Min Act: -0.0000

Data Index: 848822 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.1168. Min Act: -0.0000

Data Index: 1899479 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.0319. Min Act: -0.0000

Data Index: 702806 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.0338. Min Act: -0.0000

Data Index: 701301 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.9399. Min Act: -0.0000

Data Index: 1216502 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.9489. Min Act: -0.0000

Data Index: 334880 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 13.2501. Min Range: -13.2501

Max Act: 13.0303. Min Act: -0.0000

Data Index: 53051 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.7085. Min Act: -0.0000

Data Index: 1071208 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.6124. Min Act: -0.0000

Data Index: 271200 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.4776. Min Act: -0.0000

Data Index: 147138 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.8015. Min Act: -0.0000

Data Index: 583358 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.7031. Min Act: -0.0000

Data Index: 1551752 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.7063. Min Act: -0.0000

Data Index: 701287 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.8667. Min Act: -0.0000

Data Index: 7348 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.6324. Min Act: -0.0000

Data Index: 409299 (The Pile)

Max Activating Token Index: 465

Text #19

Max Range: 13.2501. Min Range: -13.2501

Max Act: 12.7896. Min Act: -0.0000

Data Index: 266702 (The Pile)

Max Activating Token Index: 467