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

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

Neuron 5680 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.2430. Min Act: -0.0000

Data Index: 85408 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.1946. Min Act: -0.0000

Data Index: 92230 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.2197. Min Act: -0.0000

Data Index: 302312 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1124977 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.1190. Min Act: -0.0000

Data Index: 35113 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.0795. Min Act: -0.0000

Data Index: 99080 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.0362. Min Act: -0.0000

Data Index: 327619 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.0426. Min Act: -0.0000

Data Index: 380569 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9980. Min Act: -0.0000

Data Index: 87604 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.0201. Min Act: -0.0000

Data Index: 177231 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.0131. Min Act: -0.0000

Data Index: 726117 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.2430. Min Range: -1.2430

Max Act: 1.0419. Min Act: -0.0000

Data Index: 924510 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1248273 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1263049 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1170529 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1042767 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1297120 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9728. Min Act: -0.0000

Data Index: 49752 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1207314 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.2430. Min Range: -1.2430

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1160381 (C4 (Web Text))

Max Activating Token Index: 370