Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3608 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.4452. Min Act: -0.0001

Data Index: 416339 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.3206. Min Act: -0.0001

Data Index: 1074901 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.0745. Min Act: -0.0001

Data Index: 452009 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 3.4452. Min Range: -3.4452

Max Act: 3.1497. Min Act: -0.0001

Data Index: 541455 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.8149. Min Act: -0.0001

Data Index: 1067556 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.9483. Min Act: -0.0000

Data Index: 230024 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.8000. Min Act: -0.0001

Data Index: 423696 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.9037. Min Act: -0.0001

Data Index: 1346050 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.8753. Min Act: -0.0001

Data Index: 8155 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.7233. Min Act: -0.0001

Data Index: 486962 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.9067. Min Act: -0.0001

Data Index: 541173 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.7547. Min Act: -0.0001

Data Index: 334730 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.8656. Min Act: -0.0001

Data Index: 1198394 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.6818. Min Act: -0.0001

Data Index: 106905 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.7835. Min Act: -0.0001

Data Index: 253907 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.7802. Min Act: -0.0001

Data Index: 371128 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.6200. Min Act: -0.0001

Data Index: 1330016 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.5409. Min Act: -0.0001

Data Index: 553162 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.5138. Min Act: -0.0000

Data Index: 589775 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 3.4452. Min Range: -3.4452

Max Act: 2.5079. Min Act: -0.0001

Data Index: 845760 (C4 (Web Text))

Max Activating Token Index: 900