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

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

Neuron 1526 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.7778. Min Act: -0.0000

Data Index: 342930 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.0607. Min Act: -0.0000

Data Index: 207361 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 4.7778. Min Range: -4.7778

Max Act: 4.1806. Min Act: -0.0000

Data Index: 786863 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.1551. Min Act: -0.0000

Data Index: 137169 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.7183. Min Act: -0.0000

Data Index: 127975 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.7009. Min Act: -0.0000

Data Index: 373498 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.6877. Min Act: -0.0000

Data Index: 1242827 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.6700. Min Act: -0.0000

Data Index: 837753 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.6323. Min Act: -0.0000

Data Index: 376940 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.5211. Min Act: -0.0000

Data Index: 1319826 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.6425. Min Act: -0.0001

Data Index: 1266456 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.4910. Min Act: -0.0000

Data Index: 521632 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.1303. Min Act: -0.0000

Data Index: 1152075 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.3963. Min Act: -0.0000

Data Index: 522728 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.2185. Min Act: -0.0000

Data Index: 938465 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.3542. Min Act: -0.0000

Data Index: 196369 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.4702. Min Act: -0.0000

Data Index: 899963 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.1724. Min Act: -0.0000

Data Index: 845317 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.3169. Min Act: -0.0000

Data Index: 167522 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 4.7778. Min Range: -4.7778

Max Act: 3.2943. Min Act: -0.0000

Data Index: 47272 (C4 (Web Text))

Max Activating Token Index: 225