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

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

Neuron 811 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.8552. Min Act: -0.0000

Data Index: 223553 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.8346. Min Act: -0.0000

Data Index: 158297 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1302067 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7161. Min Act: -0.0000

Data Index: 544636 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.8092. Min Act: -0.0000

Data Index: 636714 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7414. Min Act: -0.0000

Data Index: 510193 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1130141 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7207. Min Act: -0.0000

Data Index: 72153 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6558. Min Act: -0.0000

Data Index: 63357 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6932. Min Act: -0.0000

Data Index: 971988 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6618. Min Act: -0.0000

Data Index: 269969 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6568. Min Act: -0.0000

Data Index: 608298 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6795. Min Act: -0.0000

Data Index: 493638 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6694. Min Act: -0.0000

Data Index: 269553 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6899. Min Act: -0.0000

Data Index: 799140 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6552. Min Act: -0.0000

Data Index: 758180 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6988. Min Act: -0.0000

Data Index: 399542 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1327542 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6877. Min Act: -0.0000

Data Index: 190568 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1310799 (C4 (Web Text))

Max Activating Token Index: 486