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

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

Neuron 2424 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1414181 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1496631 (Python Code)

Max Activating Token Index: 353

Text #2

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1504116 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0192. Min Act: -0.0001

Data Index: 1498315 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1495865 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0153. Min Act: -0.0000

Data Index: 620651 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9625. Min Act: -0.0000

Data Index: 306341 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.2285. Min Range: -1.2285

Max Act: 1.0326. Min Act: -0.0001

Data Index: 1597874 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9620. Min Act: -0.0000

Data Index: 151313 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1513938 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9797. Min Act: -0.0000

Data Index: 510418 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9395. Min Act: -0.0001

Data Index: 1523520 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1503091 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8986. Min Act: -0.0000

Data Index: 945014 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8955. Min Act: -0.0000

Data Index: 681811 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8306. Min Act: -0.0001

Data Index: 1454874 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1068582 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8540. Min Act: -0.0000

Data Index: 513412 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8812. Min Act: -0.0000

Data Index: 832646 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.2285. Min Range: -1.2285

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1072669 (C4 (Web Text))

Max Activating Token Index: 883