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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 668 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1149399 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.4179. Min Act: -0.0000

Data Index: 1447911 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1641198 (Python Code)

Max Activating Token Index: 322

Text #3

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1266321 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1388. Min Act: -0.0000

Data Index: 1398794 (Python Code)

Max Activating Token Index: 779

Text #5

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1211. Min Act: -0.0000

Data Index: 819536 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1080864 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1437716 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1577194 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1736. Min Act: -0.0000

Data Index: 753825 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1376339 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1450662 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1512624 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 1.4179. Min Range: -1.4179

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1541796 (Python Code)

Max Activating Token Index: 316

Text #14

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1428602 (Python Code)

Max Activating Token Index: 359

Text #15

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0637. Min Act: -0.0000

Data Index: 959628 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0973. Min Act: -0.0000

Data Index: 353557 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1401356 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.1155. Min Act: -0.0000

Data Index: 693309 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.4179. Min Range: -1.4179

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1546766 (Python Code)

Max Activating Token Index: 253