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

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

Neuron 4731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1009679 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1123. Min Act: -0.0002

Data Index: 907925 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1150438 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0983. Min Act: -0.0002

Data Index: 477267 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0934. Min Act: -0.0002

Data Index: 911720 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0943. Min Act: -0.0002

Data Index: 688449 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1347707 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1294960 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0916. Min Act: -0.0002

Data Index: 228536 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0909. Min Act: -0.0002

Data Index: 491423 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1209799 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0918. Min Act: -0.0002

Data Index: 13301 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0895. Min Act: -0.0002

Data Index: 491089 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0897. Min Act: -0.0002

Data Index: 481724 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1278665 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0876. Min Act: -0.0002

Data Index: 828088 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0883. Min Act: -0.0002

Data Index: 143095 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0875. Min Act: -0.0002

Data Index: 528657 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0878. Min Act: -0.0002

Data Index: 844036 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0896. Min Act: -0.0002

Data Index: 79920 (C4 (Web Text))

Max Activating Token Index: 326