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

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

Neuron 3005 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: 1.2687. Min Range: -1.2687

Max Act: 1.2687. Min Act: -0.0000

Data Index: 775516 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1503498 (Python Code)

Max Activating Token Index: 417

Text #2

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1428687 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1544044 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1600816 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1489201 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0766. Min Act: -0.0000

Data Index: 128217 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1393766 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0504. Min Act: -0.0000

Data Index: 941996 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1544735 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1110379 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1368678 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9589. Min Act: -0.0000

Data Index: 128494 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1463962 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1456281 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1553362 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1413699 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1606562 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1543205 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1572222 (Python Code)

Max Activating Token Index: 331