Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.2552. Min Act: -0.0000

Data Index: 1088860 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.2430. Min Act: -0.0000

Data Index: 568753 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.9571. Min Act: -0.0001

Data Index: 712448 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 2.2552. Min Range: -2.2552

Max Act: 2.0031. Min Act: -0.0000

Data Index: 742050 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8671. Min Act: -0.0000

Data Index: 412980 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.9079. Min Act: -0.0000

Data Index: 49612 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8523. Min Act: -0.0001

Data Index: 1358370 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8351. Min Act: -0.0001

Data Index: 296420 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1302363 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.9025. Min Act: -0.0001

Data Index: 982274 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1225664 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8881. Min Act: -0.0000

Data Index: 318453 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.9406. Min Act: -0.0001

Data Index: 1222977 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8694. Min Act: -0.0000

Data Index: 1015497 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1001090 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8598. Min Act: -0.0001

Data Index: 735681 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.7654. Min Act: -0.0000

Data Index: 34480 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8448. Min Act: -0.0000

Data Index: 727992 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.8382. Min Act: -0.0000

Data Index: 80180 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 2.2552. Min Range: -2.2552

Max Act: 1.6215. Min Act: -0.0000

Data Index: 161362 (C4 (Web Text))

Max Activating Token Index: 280