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

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

Neuron 2104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.9835. Min Act: -0.0000

Data Index: 1237671 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.8794. Min Act: -0.0000

Data Index: 745688 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.6682. Min Act: -0.0000

Data Index: 526905 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.6677. Min Act: -0.0000

Data Index: 1564899 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.8052. Min Act: -0.0001

Data Index: 217825 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.5218. Min Act: -0.0000

Data Index: 1358962 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.3800. Min Act: -0.0000

Data Index: 752270 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.5676. Min Act: -0.0000

Data Index: 577092 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.5450. Min Act: -0.0000

Data Index: 519176 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.3999. Min Act: -0.0001

Data Index: 1247489 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.3474. Min Act: -0.0000

Data Index: 463654 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.4903. Min Act: -0.0000

Data Index: 965502 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.3326. Min Act: -0.0000

Data Index: 333165 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.2367. Min Act: -0.0000

Data Index: 572876 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.2034. Min Act: -0.0000

Data Index: 1071070 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.3085. Min Act: -0.0000

Data Index: 1499218 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.5767. Min Act: -0.0000

Data Index: 1439377 (Python Code)

Max Activating Token Index: 809

Text #17

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.1114. Min Act: -0.0000

Data Index: 653974 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 2.9835. Min Range: -2.9835

Max Act: 1.9971. Min Act: -0.0000

Data Index: 602681 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 2.9835. Min Range: -2.9835

Max Act: 2.1085. Min Act: -0.0000

Data Index: 1270892 (C4 (Web Text))

Max Activating Token Index: 539