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

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

Neuron 1997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.7990. Min Act: -0.0001

Data Index: 797345 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.7759. Min Act: -0.0000

Data Index: 812047 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.7478. Min Act: -0.0000

Data Index: 168510 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.7439. Min Act: -0.0000

Data Index: 95942 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.7104. Min Act: -0.0001

Data Index: 897780 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.6091. Min Act: -0.0000

Data Index: 397792 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1010054 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5956. Min Act: -0.0000

Data Index: 467643 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.6067. Min Act: -0.0000

Data Index: 43134 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5689. Min Act: -0.0000

Data Index: 401972 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1048650 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5456. Min Act: -0.0001

Data Index: 43945 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5614. Min Act: -0.0000

Data Index: 307313 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5344. Min Act: -0.0001

Data Index: 1104997 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5514. Min Act: -0.0001

Data Index: 569156 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5023. Min Act: -0.0000

Data Index: 569882 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.4879. Min Act: -0.0001

Data Index: 1038922 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5332. Min Act: -0.0001

Data Index: 606545 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.5124. Min Act: -0.0000

Data Index: 3435 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.7990. Min Range: -0.7990

Max Act: 0.4926. Min Act: -0.0001

Data Index: 1284255 (C4 (Web Text))

Max Activating Token Index: 563