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

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

Neuron 5150 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: 2.0512. Min Range: -2.0512

Max Act: 2.0512. Min Act: -0.0002

Data Index: 777117 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.8115. Min Act: -0.0002

Data Index: 1177906 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.8288. Min Act: -0.0002

Data Index: 877844 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.8120. Min Act: -0.0003

Data Index: 73616 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.7704. Min Act: -0.0003

Data Index: 809156 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.8265. Min Act: -0.0002

Data Index: 1247196 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.7483. Min Act: -0.0003

Data Index: 949246 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6877. Min Act: -0.0002

Data Index: 1124418 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6795. Min Act: -0.0002

Data Index: 1276241 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6360. Min Act: -0.0002

Data Index: 237343 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6530. Min Act: -0.0002

Data Index: 1093013 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6138. Min Act: -0.0002

Data Index: 871286 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6409. Min Act: -0.0002

Data Index: 154480 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6038. Min Act: -0.0002

Data Index: 329096 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6400. Min Act: -0.0002

Data Index: 329994 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6379. Min Act: -0.0002

Data Index: 1185256 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6181. Min Act: -0.0002

Data Index: 349882 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.5714. Min Act: -0.0002

Data Index: 50642 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.6570. Min Act: -0.0002

Data Index: 786052 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 2.0512. Min Range: -2.0512

Max Act: 1.5903. Min Act: -0.0002

Data Index: 909868 (C4 (Web Text))

Max Activating Token Index: 290