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

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

Neuron 519 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.9015. Min Act: -0.0001

Data Index: 696757 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1342856 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7400. Min Act: -0.0001

Data Index: 633824 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7310. Min Act: -0.0001

Data Index: 816295 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.7395. Min Act: -0.0001

Data Index: 825714 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6891. Min Act: -0.0001

Data Index: 1223777 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6600. Min Act: -0.0001

Data Index: 623047 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6552. Min Act: -0.0001

Data Index: 467333 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6547. Min Act: -0.0001

Data Index: 478211 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6326. Min Act: -0.0001

Data Index: 837626 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6232. Min Act: -0.0001

Data Index: 248159 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5981. Min Act: -0.0001

Data Index: 745972 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5719. Min Act: -0.0001

Data Index: 599541 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6047. Min Act: -0.0001

Data Index: 1011555 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1184953 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5747. Min Act: -0.0001

Data Index: 1057526 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5721. Min Act: -0.0001

Data Index: 1152296 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5918. Min Act: -0.0001

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5876. Min Act: -0.0001

Data Index: 205074 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.9015. Min Range: -0.9015

Max Act: 0.5629. Min Act: -0.0001

Data Index: 567178 (C4 (Web Text))

Max Activating Token Index: 291