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

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

Neuron 472 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8178. Min Range: -2.8178

Max Act: 2.8178. Min Act: -0.0000

Data Index: 172451 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 2.8178. Min Range: -2.8178

Max Act: 2.4878. Min Act: -0.0000

Data Index: 684736 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.9433. Min Act: -0.0000

Data Index: 401046 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.9253. Min Act: -0.0000

Data Index: 1122253 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.8822. Min Act: -0.0000

Data Index: 1156670 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.7440. Min Act: -0.0000

Data Index: 1354391 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.7240. Min Act: -0.0000

Data Index: 190751 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1277617 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.6612. Min Act: -0.0000

Data Index: 197245 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.7445. Min Act: -0.0000

Data Index: 871701 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.7470. Min Act: -0.0000

Data Index: 945854 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.7068. Min Act: -0.0000

Data Index: 865757 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.6091. Min Act: -0.0000

Data Index: 351018 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.5393. Min Act: -0.0000

Data Index: 851956 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.6442. Min Act: -0.0000

Data Index: 105133 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.6396. Min Act: -0.0000

Data Index: 199570 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.6540. Min Act: -0.0000

Data Index: 785780 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.6294. Min Act: -0.0000

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1079639 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 2.8178. Min Range: -2.8178

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1235609 (C4 (Web Text))

Max Activating Token Index: 332