Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2012 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.8656. Min Act: -0.0002

Data Index: 153442 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.8401. Min Act: -0.0002

Data Index: 433539 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.8443. Min Act: -0.0002

Data Index: 974434 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7356. Min Act: -0.0002

Data Index: 778254 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6919. Min Act: -0.0002

Data Index: 353888 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7138. Min Act: -0.0002

Data Index: 93309 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7199. Min Act: -0.0001

Data Index: 237156 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7129. Min Act: -0.0002

Data Index: 921260 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7697. Min Act: -0.0001

Data Index: 640689 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7288. Min Act: -0.0001

Data Index: 886102 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1228236 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.7058. Min Act: -0.0001

Data Index: 637007 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6788. Min Act: -0.0001

Data Index: 667125 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6562. Min Act: -0.0002

Data Index: 271763 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6542. Min Act: -0.0001

Data Index: 627572 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6113. Min Act: -0.0002

Data Index: 333098 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6405. Min Act: -0.0001

Data Index: 870170 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5795. Min Act: -0.0002

Data Index: 1162052 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.5613. Min Act: -0.0002

Data Index: 471115 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.8656. Min Range: -0.8656

Max Act: 0.6181. Min Act: -0.0001

Data Index: 1118954 (C4 (Web Text))

Max Activating Token Index: 57