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

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

Neuron 1760 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: 1.4624. Min Range: -1.4624

Max Act: 1.4624. Min Act: -0.0000

Data Index: 417220 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1999. Min Act: -0.0000

Data Index: 511797 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1307958 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.3083. Min Act: -0.0000

Data Index: 114834 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1339507 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1838. Min Act: -0.0000

Data Index: 360022 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1946. Min Act: -0.0000

Data Index: 468217 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.2251. Min Act: -0.0000

Data Index: 617408 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1349. Min Act: -0.0000

Data Index: 311775 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0972. Min Act: -0.0000

Data Index: 829594 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1571. Min Act: -0.0000

Data Index: 554543 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1111. Min Act: -0.0000

Data Index: 438353 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1103. Min Act: -0.0000

Data Index: 158900 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1659. Min Act: -0.0000

Data Index: 71893 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0997. Min Act: -0.0000

Data Index: 553321 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1154. Min Act: -0.0000

Data Index: 7378 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0634. Min Act: -0.0000

Data Index: 375965 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.1294. Min Act: -0.0000

Data Index: 151122 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0861. Min Act: -0.0000

Data Index: 371469 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.4624. Min Range: -1.4624

Max Act: 1.0839. Min Act: -0.0000

Data Index: 264958 (C4 (Web Text))

Max Activating Token Index: 354