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

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

Neuron 263 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: 3.7850. Min Range: -3.7850

Max Act: 3.6917. Min Act: -0.0001

Data Index: 639965 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.7850. Min Act: -0.0000

Data Index: 633513 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.3855. Min Act: -0.0000

Data Index: 1035536 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.3841. Min Act: -0.0000

Data Index: 602025 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.3261. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.2142. Min Act: -0.0001

Data Index: 467477 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.1583. Min Act: -0.0000

Data Index: 1076696 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.1065. Min Act: -0.0000

Data Index: 1279309 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.8809. Min Act: -0.0000

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.0132. Min Act: -0.0000

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.9841. Min Act: -0.0001

Data Index: 674499 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.9400. Min Act: -0.0000

Data Index: 1322434 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.7791. Min Act: -0.0000

Data Index: 135126 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.7700. Min Act: -0.0000

Data Index: 1262341 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.9403. Min Act: -0.0000

Data Index: 175978 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.9457. Min Act: -0.0001

Data Index: 591491 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.9973. Min Act: -0.0001

Data Index: 235241 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.9190. Min Act: -0.0001

Data Index: 248563 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.6908. Min Act: -0.0000

Data Index: 270491 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 3.7850. Min Range: -3.7850

Max Act: 2.6848. Min Act: -0.0000

Data Index: 695908 (C4 (Web Text))

Max Activating Token Index: 129