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

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

Neuron 4741 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0546. Min Range: -2.0546

Max Act: 2.0546. Min Act: -0.0000

Data Index: 750108 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 2.0546. Min Range: -2.0546

Max Act: 2.0263. Min Act: -0.0000

Data Index: 996657 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.8814. Min Act: -0.0000

Data Index: 1330225 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.7719. Min Act: -0.0000

Data Index: 303279 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1303969 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.7445. Min Act: -0.0000

Data Index: 285370 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.6549. Min Act: -0.0000

Data Index: 929698 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.4994. Min Act: -0.0000

Data Index: 44278 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.5403. Min Act: -0.0000

Data Index: 606950 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1012432 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.2882. Min Act: -0.0000

Data Index: 964715 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.3300. Min Act: -0.0000

Data Index: 553019 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.2846. Min Act: -0.0000

Data Index: 385898 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.5120. Min Act: -0.0000

Data Index: 1216953 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.2342. Min Act: -0.0000

Data Index: 70824 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.3929. Min Act: -0.0000

Data Index: 345706 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.3939. Min Act: -0.0000

Data Index: 832128 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1027361 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1584978 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 2.0546. Min Range: -2.0546

Max Act: 1.3161. Min Act: -0.0000

Data Index: 934320 (C4 (Web Text))

Max Activating Token Index: 831