Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0896. Min Act: -0.0001

Data Index: 1408513 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: -0.0001

Data Index: 1389045 (Python Code)

Max Activating Token Index: 512

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0744. Min Act: -0.0001

Data Index: 1424718 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1382761 (Python Code)

Max Activating Token Index: 619

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9394. Min Act: -0.0001

Data Index: 1211205 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1394214 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8436. Min Act: -0.0001

Data Index: 1576200 (Python Code)

Max Activating Token Index: 566

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9477. Min Act: -0.0001

Data Index: 1569685 (Python Code)

Max Activating Token Index: 835

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8258. Min Act: -0.0001

Data Index: 1366659 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8864. Min Act: -0.0001

Data Index: 1626456 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1622647 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8236. Min Act: -0.0001

Data Index: 1571865 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1446189 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7915. Min Act: -0.0001

Data Index: 1110860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.6893. Min Act: -0.0001

Data Index: 1504187 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1572145 (Python Code)

Max Activating Token Index: 566

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8800. Min Act: -0.0001

Data Index: 1535825 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7485. Min Act: -0.0001

Data Index: 1481448 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7978. Min Act: -0.0001

Data Index: 1631509 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.7664. Min Act: -0.0001

Data Index: 1541170 (Python Code)

Max Activating Token Index: 881