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

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

Neuron 4347 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: 1.8644. Min Range: -1.8644

Max Act: 1.8644. Min Act: -0.0002

Data Index: 429015 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.8146. Min Act: -0.0002

Data Index: 1309722 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.8041. Min Act: -0.0002

Data Index: 1228330 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7813. Min Act: -0.0002

Data Index: 250584 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7507. Min Act: -0.0002

Data Index: 937620 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7426. Min Act: -0.0002

Data Index: 1245748 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7129. Min Act: -0.0002

Data Index: 1038504 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7302. Min Act: -0.0002

Data Index: 1303026 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7394. Min Act: -0.0002

Data Index: 683197 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6965. Min Act: -0.0002

Data Index: 240137 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7239. Min Act: -0.0002

Data Index: 666839 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6844. Min Act: -0.0002

Data Index: 886728 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7003. Min Act: -0.0002

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6642. Min Act: -0.0002

Data Index: 467647 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6634. Min Act: -0.0002

Data Index: 946299 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6772. Min Act: -0.0002

Data Index: 1177572 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.7024. Min Act: -0.0002

Data Index: 774567 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6378. Min Act: -0.0002

Data Index: 570561 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6258. Min Act: -0.0003

Data Index: 16113 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.8644. Min Range: -1.8644

Max Act: 1.6098. Min Act: -0.0002

Data Index: 350025 (C4 (Web Text))

Max Activating Token Index: 490