Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5570. Min Act: -0.0001

Data Index: 1004165 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.5101. Min Act: -0.0000

Data Index: 305942 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4525. Min Act: -0.0001

Data Index: 1525619 (Python Code)

Max Activating Token Index: 687

Text #3

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4673. Min Act: -0.0000

Data Index: 890522 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4501. Min Act: -0.0001

Data Index: 1415392 (Python Code)

Max Activating Token Index: 868

Text #5

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4026. Min Act: -0.0001

Data Index: 1651844 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1430353 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4089. Min Act: -0.0001

Data Index: 1649750 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1055804 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1540049 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3920. Min Act: -0.0000

Data Index: 319317 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1153879 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1287977 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1223563 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3525. Min Act: -0.0001

Data Index: 1492183 (Python Code)

Max Activating Token Index: 404

Text #15

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3789. Min Act: -0.0000

Data Index: 624432 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3786. Min Act: -0.0000

Data Index: 414839 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3683. Min Act: -0.0000

Data Index: 603978 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3552. Min Act: -0.0000

Data Index: 553974 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.5570. Min Range: -0.5570

Max Act: 0.3796. Min Act: -0.0000

Data Index: 258111 (C4 (Web Text))

Max Activating Token Index: 348