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

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

Neuron 5562 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1370290 (Python Code)

Max Activating Token Index: 603

Text #1

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1606577 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1582708 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2177. Min Act: -0.0000

Data Index: 461588 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1871. Min Act: -0.0000

Data Index: 26073 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1667. Min Act: -0.0000

Data Index: 513870 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1451314 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1619273 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1445071 (Python Code)

Max Activating Token Index: 633

Text #9

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1030206 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1259482 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1370970 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1654756 (Python Code)

Max Activating Token Index: 603

Text #13

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1594224 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1228364 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1563839 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1577972 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1486544 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1544254 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.1533. Min Act: -0.0000

Data Index: 150063 (C4 (Web Text))

Max Activating Token Index: 497