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

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

Neuron 1881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1561977 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.5360. Min Act: -0.0001

Data Index: 1492813 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4834. Min Act: -0.0000

Data Index: 999762 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4913. Min Act: -0.0000

Data Index: 852826 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4619. Min Act: -0.0001

Data Index: 689392 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4686. Min Act: -0.0001

Data Index: 1287879 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4901. Min Act: -0.0001

Data Index: 41127 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4575. Min Act: -0.0000

Data Index: 338519 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4461. Min Act: -0.0001

Data Index: 1403801 (Python Code)

Max Activating Token Index: 744

Text #9

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1281741 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4459. Min Act: -0.0001

Data Index: 1124664 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4397. Min Act: -0.0001

Data Index: 265888 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1600227 (Python Code)

Max Activating Token Index: 976

Text #13

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4097. Min Act: -0.0000

Data Index: 170766 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4090. Min Act: -0.0001

Data Index: 1510057 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4099. Min Act: -0.0001

Data Index: 1477873 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4015. Min Act: -0.0001

Data Index: 1515543 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4275. Min Act: -0.0001

Data Index: 416150 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.4032. Min Act: -0.0001

Data Index: 1127690 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.5543. Min Range: -0.5543

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1258089 (C4 (Web Text))

Max Activating Token Index: 992