Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2476 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.1187. Min Act: -0.0002

Data Index: 1578171 (Python Code)

Max Activating Token Index: 735

Text #1

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0611. Min Act: -0.0002

Data Index: 1616047 (Python Code)

Max Activating Token Index: 863

Text #2

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0042. Min Act: -0.0002

Data Index: 1622266 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0062. Min Act: -0.0002

Data Index: 1462688 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 1.1187. Min Range: -1.1187

Max Act: 1.0058. Min Act: -0.0002

Data Index: 1598056 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9375. Min Act: -0.0002

Data Index: 1516350 (Python Code)

Max Activating Token Index: 408

Text #6

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9469. Min Act: -0.0002

Data Index: 1152873 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.9174. Min Act: -0.0002

Data Index: 1474752 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8917. Min Act: -0.0002

Data Index: 1477790 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8859. Min Act: -0.0002

Data Index: 1641635 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8860. Min Act: -0.0002

Data Index: 1086431 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8684. Min Act: -0.0002

Data Index: 565551 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8736. Min Act: -0.0002

Data Index: 1457254 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8641. Min Act: -0.0002

Data Index: 210799 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8823. Min Act: -0.0002

Data Index: 1515130 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8835. Min Act: -0.0002

Data Index: 1365477 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8634. Min Act: -0.0002

Data Index: 1368632 (Python Code)

Max Activating Token Index: 812

Text #17

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8653. Min Act: -0.0002

Data Index: 689360 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8710. Min Act: -0.0002

Data Index: 1477367 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 1.1187. Min Range: -1.1187

Max Act: 0.8485. Min Act: -0.0001

Data Index: 447024 (C4 (Web Text))

Max Activating Token Index: 382