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

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

Neuron 1961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3584. Min Range: -2.3584

Max Act: 2.3584. Min Act: -0.0000

Data Index: 1477493 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 2.3584. Min Range: -2.3584

Max Act: 2.3444. Min Act: -0.0000

Data Index: 1611623 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 2.3584. Min Range: -2.3584

Max Act: 2.1822. Min Act: -0.0000

Data Index: 1465967 (Python Code)

Max Activating Token Index: 457

Text #3

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.9432. Min Act: -0.0000

Data Index: 1540908 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.9346. Min Act: -0.0000

Data Index: 1459379 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8796. Min Act: -0.0000

Data Index: 1478012 (Python Code)

Max Activating Token Index: 286

Text #6

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.9601. Min Act: -0.0000

Data Index: 1625735 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1411879 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8666. Min Act: -0.0000

Data Index: 1539400 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8033. Min Act: -0.0000

Data Index: 1648414 (Python Code)

Max Activating Token Index: 86

Text #10

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8954. Min Act: -0.0000

Data Index: 1645679 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1507592 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8453. Min Act: -0.0000

Data Index: 1441721 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8970. Min Act: -0.0000

Data Index: 1499646 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.9807. Min Act: -0.0000

Data Index: 1656887 (Python Code)

Max Activating Token Index: 739

Text #15

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8137. Min Act: -0.0000

Data Index: 1581138 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8173. Min Act: -0.0000

Data Index: 1381075 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8434. Min Act: -0.0000

Data Index: 1637537 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.8509. Min Act: -0.0000

Data Index: 1503198 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 2.3584. Min Range: -2.3584

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1541444 (Python Code)

Max Activating Token Index: 332