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

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

Neuron 4724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.7743. Min Act: -0.0000

Data Index: 154194 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.8590. Min Act: -0.0000

Data Index: 1266339 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.5337. Min Act: -0.0000

Data Index: 15802 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.4737. Min Act: -0.0000

Data Index: 76632 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.4585. Min Act: -0.0000

Data Index: 81094 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.4586. Min Act: -0.0000

Data Index: 932748 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.5142. Min Act: -0.0000

Data Index: 751218 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.4255. Min Act: -0.0000

Data Index: 47967 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.2888. Min Act: -0.0000

Data Index: 266167 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.2669. Min Act: -0.0000

Data Index: 384902 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.3438. Min Act: -0.0000

Data Index: 1129322 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.3300. Min Act: -0.0000

Data Index: 402073 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1027812 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.2945. Min Act: -0.0000

Data Index: 1203603 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.3007. Min Act: -0.0000

Data Index: 783467 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1226628 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.1271. Min Act: -0.0000

Data Index: 194888 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1148248 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1215925 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.8590. Min Range: -1.8590

Max Act: 1.2434. Min Act: -0.0000

Data Index: 938602 (C4 (Web Text))

Max Activating Token Index: 440