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

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

Neuron 3375 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.9467. Min Act: -0.0000

Data Index: 440387 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.5110. Min Act: -0.0000

Data Index: 1341284 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1062440 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.3297. Min Act: -0.0000

Data Index: 627594 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.3509. Min Act: -0.0000

Data Index: 623625 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.4520. Min Act: -0.0000

Data Index: 1190701 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.0811. Min Act: -0.0000

Data Index: 998896 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.0333. Min Act: -0.0000

Data Index: 229442 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1132502 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1235914 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8398. Min Act: -0.0000

Data Index: 737485 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8629. Min Act: -0.0000

Data Index: 794401 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8600. Min Act: -0.0000

Data Index: 483992 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 2.9467. Min Range: -2.9467

Max Act: 2.0732. Min Act: -0.0000

Data Index: 636901 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.9062. Min Act: -0.0000

Data Index: 527928 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8896. Min Act: -0.0000

Data Index: 658316 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.7763. Min Act: -0.0000

Data Index: 710139 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.8463. Min Act: -0.0000

Data Index: 839865 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.7449. Min Act: -0.0000

Data Index: 271800 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 2.9467. Min Range: -2.9467

Max Act: 1.7298. Min Act: -0.0000

Data Index: 955925 (C4 (Web Text))

Max Activating Token Index: 237