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

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

Neuron 1004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9373. Min Act: -0.0000

Data Index: 833604 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9886. Min Act: -0.0000

Data Index: 411091 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9500. Min Act: 0.0000

Data Index: 397639 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1268129 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9186. Min Act: -0.0000

Data Index: 640528 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8858. Min Act: -0.0000

Data Index: 903217 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.9418. Min Act: -0.0000

Data Index: 238220 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8763. Min Act: -0.0000

Data Index: 868500 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8961. Min Act: 0.0000

Data Index: 1126504 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8723. Min Act: -0.0000

Data Index: 723740 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8498. Min Act: -0.0000

Data Index: 795365 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1192227 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1179523 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1268558 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7516. Min Act: -0.0000

Data Index: 611594 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7854. Min Act: -0.0000

Data Index: 802128 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1051002 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.7549. Min Act: -0.0000

Data Index: 267912 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.9886. Min Range: -0.9886

Max Act: 0.6757. Min Act: -0.0000

Data Index: 6066 (C4 (Web Text))

Max Activating Token Index: 632