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

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

Neuron 2803 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: 3.2492. Min Range: -3.2492

Max Act: 3.2492. Min Act: -0.0000

Data Index: 1492045 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.9549. Min Act: -0.0000

Data Index: 1650188 (Python Code)

Max Activating Token Index: 468

Text #2

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.7864. Min Act: -0.0000

Data Index: 1364973 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.6001. Min Act: -0.0000

Data Index: 1490555 (Python Code)

Max Activating Token Index: 578

Text #4

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.4027. Min Act: -0.0000

Data Index: 328260 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.2963. Min Act: -0.0000

Data Index: 1423756 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.2682. Min Act: -0.0000

Data Index: 953533 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.3896. Min Act: -0.0000

Data Index: 1055886 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.2711. Min Act: -0.0000

Data Index: 1647487 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.3697. Min Act: -0.0000

Data Index: 393477 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1444902 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.0151. Min Act: -0.0000

Data Index: 963474 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.2308. Min Act: -0.0000

Data Index: 1436437 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.3509. Min Act: -0.0000

Data Index: 1581912 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.1984. Min Act: -0.0000

Data Index: 1424675 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.2056. Min Act: -0.0000

Data Index: 1087757 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.3048. Min Act: -0.0000

Data Index: 525467 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.1588. Min Act: -0.0000

Data Index: 198221 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 3.2492. Min Range: -3.2492

Max Act: 2.1324. Min Act: -0.0000

Data Index: 861943 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 3.2492. Min Range: -3.2492

Max Act: 1.9959. Min Act: -0.0000

Data Index: 1038505 (C4 (Web Text))

Max Activating Token Index: 620