Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4960. Min Act: -0.0000

Data Index: 674202 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3344. Min Act: -0.0000

Data Index: 18389 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3922. Min Act: -0.0000

Data Index: 114437 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1350900 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2931. Min Act: -0.0000

Data Index: 45275 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1181086 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3080. Min Act: -0.0000

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1080092 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2551. Min Act: -0.0000

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1084174 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1089403 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1866. Min Act: -0.0000

Data Index: 30554 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1787. Min Act: 0.0000

Data Index: 905831 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1898. Min Act: -0.0000

Data Index: 232873 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2087. Min Act: -0.0000

Data Index: 116258 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3530. Min Act: -0.0000

Data Index: 343977 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1690. Min Act: -0.0000

Data Index: 383214 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1384. Min Act: -0.0000

Data Index: 392364 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.1697. Min Act: -0.0000

Data Index: 998623 (C4 (Web Text))

Max Activating Token Index: 650