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

Dataset: The Pile

Neuron 521 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: 0.8980. Min Range: -0.8980

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1406789 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1332571 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.8415. Min Act: -0.0000

Data Index: 367083 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.8197. Min Act: -0.0000

Data Index: 923135 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7793. Min Act: -0.0000

Data Index: 308582 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7691. Min Act: -0.0000

Data Index: 765165 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6387. Min Act: -0.0000

Data Index: 180179 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.8501. Min Act: -0.0000

Data Index: 437739 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1949687 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7005. Min Act: -0.0000

Data Index: 106692 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1751705 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.7212. Min Act: -0.0000

Data Index: 869750 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6934. Min Act: -0.0000

Data Index: 451900 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6860. Min Act: -0.0000

Data Index: 67756 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1515916 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1763179 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1116569 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1554811 (The Pile)

Max Activating Token Index: 252

Text #18

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1464306 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 0.8980. Min Range: -0.8980

Max Act: 0.6375. Min Act: -0.0000

Data Index: 998813 (The Pile)

Max Activating Token Index: 552