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

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

Neuron 555 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.7117. Min Act: -0.0000

Data Index: 39667 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.3289. Min Act: -0.0000

Data Index: 1072800 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.7018. Min Act: -0.0000

Data Index: 1124654 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.0092. Min Act: -0.0000

Data Index: 971017 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 3.7117. Min Range: -3.7117

Max Act: 3.0279. Min Act: -0.0000

Data Index: 1118913 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.6891. Min Act: -0.0000

Data Index: 1050141 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.7684. Min Act: -0.0000

Data Index: 1359436 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.5827. Min Act: -0.0000

Data Index: 753035 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.8309. Min Act: -0.0000

Data Index: 1318919 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1184695 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.5409. Min Act: -0.0000

Data Index: 250717 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.6561. Min Act: -0.0000

Data Index: 169252 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.2911. Min Act: -0.0000

Data Index: 1180096 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.6401. Min Act: -0.0000

Data Index: 1315089 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.6964. Min Act: -0.0000

Data Index: 549765 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.5663. Min Act: -0.0000

Data Index: 44616 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.3282. Min Act: -0.0000

Data Index: 760811 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.2886. Min Act: -0.0000

Data Index: 197401 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.3170. Min Act: -0.0000

Data Index: 367210 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.7117. Min Range: -3.7117

Max Act: 2.4893. Min Act: -0.0000

Data Index: 706719 (C4 (Web Text))

Max Activating Token Index: 569