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

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

Neuron 4469 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3605. Min Act: 0.0000

Data Index: 1483349 (Python Code)

Max Activating Token Index: 634

Text #1

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1611401 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1426532 (Python Code)

Max Activating Token Index: 433

Text #3

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1547029 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1404987 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1551446 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1586207 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1522232 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2725. Min Act: 0.0000

Data Index: 1374183 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1509254 (Python Code)

Max Activating Token Index: 857

Text #10

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1481932 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1443402 (Python Code)

Max Activating Token Index: 378

Text #12

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1362407 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1368385 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1599992 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.3020. Min Act: 0.0000

Data Index: 1484598 (Python Code)

Max Activating Token Index: 717

Text #16

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2507. Min Act: 0.0000

Data Index: 1360537 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2537. Min Act: 0.0000

Data Index: 1596870 (Python Code)

Max Activating Token Index: 412

Text #18

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1473302 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.3605. Min Range: -0.3605

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1476705 (Python Code)

Max Activating Token Index: 151