Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1264605 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4755. Min Act: -0.0000

Data Index: 529131 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1195008 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1228244 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3425. Min Act: -0.0000

Data Index: 677418 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3538. Min Act: -0.0000

Data Index: 631071 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3600. Min Act: -0.0000

Data Index: 122103 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3473. Min Act: -0.0000

Data Index: 549470 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3458. Min Act: -0.0000

Data Index: 202714 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1346450 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1124585 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3092. Min Act: -0.0000

Data Index: 993307 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3096. Min Act: -0.0000

Data Index: 398190 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1262823 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3081. Min Act: -0.0000

Data Index: 881254 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1151291 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3018. Min Act: -0.0000

Data Index: 955813 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3110. Min Act: -0.0000

Data Index: 2592 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1200282 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.2885. Min Act: -0.0000

Data Index: 416201 (C4 (Web Text))

Max Activating Token Index: 279