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

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

Neuron 2417 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7093. Min Range: -2.7093

Max Act: 2.5998. Min Act: -0.0000

Data Index: 1253486 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 2.7093. Min Range: -2.7093

Max Act: 2.5835. Min Act: -0.0000

Data Index: 77475 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 2.7093. Min Range: -2.7093

Max Act: 2.7093. Min Act: -0.0000

Data Index: 787809 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.8710. Min Act: -0.0000

Data Index: 279648 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.9852. Min Act: -0.0000

Data Index: 268237 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.7866. Min Act: -0.0000

Data Index: 1199752 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.7243. Min Act: -0.0000

Data Index: 273084 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.6096. Min Act: -0.0000

Data Index: 368349 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.5688. Min Act: -0.0000

Data Index: 219921 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.5400. Min Act: -0.0000

Data Index: 723853 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.5140. Min Act: -0.0000

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4771. Min Act: -0.0000

Data Index: 559627 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4125. Min Act: -0.0000

Data Index: 386922 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1271158 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1025555 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4498. Min Act: -0.0000

Data Index: 385849 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4092. Min Act: -0.0000

Data Index: 45467 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.4026. Min Act: -0.0000

Data Index: 951292 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1145704 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 2.7093. Min Range: -2.7093

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1219988 (C4 (Web Text))

Max Activating Token Index: 398