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

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

Neuron 4578 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: 2.1835. Min Range: -2.1835

Max Act: 2.1835. Min Act: -0.0000

Data Index: 62018 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.7763. Min Act: -0.0000

Data Index: 157104 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 2.1835. Min Range: -2.1835

Max Act: 2.0625. Min Act: -0.0000

Data Index: 1221970 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.8594. Min Act: -0.0000

Data Index: 166845 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6871. Min Act: -0.0000

Data Index: 694132 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.5917. Min Act: -0.0000

Data Index: 225143 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1135246 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.8863. Min Act: -0.0000

Data Index: 401774 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.5527. Min Act: -0.0000

Data Index: 111414 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.8520. Min Act: -0.0000

Data Index: 285755 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.5499. Min Act: -0.0000

Data Index: 522400 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.8328. Min Act: -0.0000

Data Index: 1207740 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.7201. Min Act: -0.0000

Data Index: 703241 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6887. Min Act: -0.0000

Data Index: 90526 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6846. Min Act: -0.0000

Data Index: 529163 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6914. Min Act: -0.0000

Data Index: 730294 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6866. Min Act: -0.0000

Data Index: 827906 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.6889. Min Act: -0.0000

Data Index: 857168 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.5920. Min Act: -0.0000

Data Index: 226350 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.4840. Min Act: -0.0000

Data Index: 69567 (C4 (Web Text))

Max Activating Token Index: 834