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

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

Neuron 3039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1399803 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1505187 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1648492 (Python Code)

Max Activating Token Index: 467

Text #3

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1626334 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1401765 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0667. Min Act: -0.0001

Data Index: 1552989 (Python Code)

Max Activating Token Index: 386

Text #6

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1376643 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1482860 (Python Code)

Max Activating Token Index: 501

Text #8

Max Range: 1.3545. Min Range: -1.3545

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1443153 (Python Code)

Max Activating Token Index: 330

Text #9

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1546809 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1643957 (Python Code)

Max Activating Token Index: 732

Text #11

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1511811 (Python Code)

Max Activating Token Index: 116

Text #12

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1424599 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1461384 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1561529 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1637923 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1408352 (Python Code)

Max Activating Token Index: 602

Text #17

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1364642 (Python Code)

Max Activating Token Index: 589

Text #18

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1505727 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 1.3545. Min Range: -1.3545

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1395840 (Python Code)

Max Activating Token Index: 253