Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3284 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1155520 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0001

Data Index: 622781 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0903. Min Act: -0.0001

Data Index: 943663 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0887. Min Act: -0.0001

Data Index: 601753 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0771. Min Act: -0.0001

Data Index: 148387 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0824. Min Act: -0.0001

Data Index: 703355 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1029621 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0810. Min Act: -0.0001

Data Index: 332325 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0788. Min Act: -0.0001

Data Index: 581621 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1260620 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1147143 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1219627 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0766. Min Act: -0.0001

Data Index: 911358 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0774. Min Act: -0.0001

Data Index: 417534 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0769. Min Act: -0.0001

Data Index: 157707 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0786. Min Act: -0.0001

Data Index: 217908 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1020446 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0787. Min Act: -0.0001

Data Index: 711831 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0753. Min Act: -0.0001

Data Index: 448408 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0725. Min Act: -0.0001

Data Index: 43588 (C4 (Web Text))

Max Activating Token Index: 574