Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.3337. Min Act: -0.0000

Data Index: 521530 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.3346. Min Act: -0.0000

Data Index: 1059846 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.2692. Min Act: -0.0000

Data Index: 609168 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1739. Min Act: -0.0000

Data Index: 793895 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1581. Min Act: -0.0001

Data Index: 371762 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.2529. Min Act: -0.0001

Data Index: 702536 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1488. Min Act: -0.0001

Data Index: 794186 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1778. Min Act: -0.0000

Data Index: 78651 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.2069. Min Act: -0.0000

Data Index: 936499 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1169. Min Act: -0.0001

Data Index: 709254 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.0904. Min Act: -0.0001

Data Index: 680809 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1840. Min Act: -0.0000

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.0740. Min Act: -0.0000

Data Index: 172872 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1303. Min Act: -0.0000

Data Index: 238280 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1256989 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.0711. Min Act: -0.0000

Data Index: 774746 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1042. Min Act: -0.0000

Data Index: 492090 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.0207. Min Act: -0.0001

Data Index: 1654630 (Python Code)

Max Activating Token Index: 748

Text #18

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.0901. Min Act: -0.0001

Data Index: 30156 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.3346. Min Range: -1.3346

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1283877 (C4 (Web Text))

Max Activating Token Index: 220