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

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

Neuron 3955 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.5262. Min Act: -0.0000

Data Index: 1421303 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.5313. Min Act: -0.0000

Data Index: 966140 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1456584 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1505428 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1445276 (Python Code)

Max Activating Token Index: 931

Text #5

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1027317 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.3345. Min Act: -0.0000

Data Index: 785181 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1376436 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0929. Min Act: -0.0000

Data Index: 996262 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.5313. Min Range: -1.5313

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1081805 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1612230 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1567636 (Python Code)

Max Activating Token Index: 129

Text #13

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0167. Min Act: -0.0000

Data Index: 183924 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1586552 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1393811 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 1.5313. Min Range: -1.5313

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1480046 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1491872 (Python Code)

Max Activating Token Index: 482

Text #18

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1478713 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 1.5313. Min Range: -1.5313

Max Act: 1.0667. Min Act: -0.0000

Data Index: 441041 (C4 (Web Text))

Max Activating Token Index: 380