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

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

Neuron 2192 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: 1.0683. Min Range: -1.0683

Max Act: 1.0683. Min Act: -0.0001

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.9554. Min Act: -0.0001

Data Index: 1078393 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.0683. Min Range: -1.0683

Max Act: 1.0005. Min Act: -0.0001

Data Index: 1076952 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.9605. Min Act: -0.0001

Data Index: 818527 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.9479. Min Act: -0.0001

Data Index: 85415 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.9722. Min Act: -0.0000

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.9182. Min Act: -0.0001

Data Index: 607676 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8608. Min Act: -0.0001

Data Index: 1128991 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8474. Min Act: -0.0001

Data Index: 173729 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8401. Min Act: -0.0001

Data Index: 365189 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1282422 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8080. Min Act: -0.0001

Data Index: 874182 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8032. Min Act: -0.0001

Data Index: 941839 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.8121. Min Act: -0.0001

Data Index: 6831 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.7540. Min Act: -0.0001

Data Index: 661356 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.7266. Min Act: -0.0001

Data Index: 275372 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.7082. Min Act: -0.0001

Data Index: 1160458 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.7070. Min Act: -0.0000

Data Index: 338466 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1130225 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.0683. Min Range: -1.0683

Max Act: 0.7018. Min Act: -0.0001

Data Index: 671110 (C4 (Web Text))

Max Activating Token Index: 554