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

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

Neuron 4335 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.2107. Min Act: -0.0000

Data Index: 1282947 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1255132 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.2058. Min Act: -0.0000

Data Index: 1259247 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.1526. Min Act: -0.0000

Data Index: 896447 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.1405. Min Act: -0.0000

Data Index: 1307444 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.1336. Min Act: -0.0000

Data Index: 101614 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1303179 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.1918. Min Act: -0.0000

Data Index: 487604 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.0498. Min Act: -0.0000

Data Index: 290789 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1210764 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9825. Min Act: -0.0000

Data Index: 434699 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1602498 (Python Code)

Max Activating Token Index: 923

Text #12

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.1188. Min Act: -0.0000

Data Index: 545646 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9089. Min Act: -0.0000

Data Index: 755063 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.0015. Min Act: -0.0000

Data Index: 140556 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.2814. Min Range: -1.2814

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1643025 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9457. Min Act: -0.0000

Data Index: 292199 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1277592 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9639. Min Act: -0.0000

Data Index: 835951 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.2814. Min Range: -1.2814

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1178264 (C4 (Web Text))

Max Activating Token Index: 726