Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 243 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4629. Min Act: -0.0001

Data Index: 435864 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4315. Min Act: -0.0001

Data Index: 72754 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4799. Min Act: -0.0001

Data Index: 388149 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3856. Min Act: -0.0001

Data Index: 412408 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4180. Min Act: -0.0001

Data Index: 559157 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1266763 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3819. Min Act: -0.0001

Data Index: 449863 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1047441 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4314. Min Act: -0.0001

Data Index: 282969 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4274. Min Act: -0.0001

Data Index: 825297 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3708. Min Act: -0.0001

Data Index: 962355 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4061. Min Act: -0.0001

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3715. Min Act: -0.0001

Data Index: 795872 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3942. Min Act: -0.0001

Data Index: 1299344 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3897. Min Act: -0.0001

Data Index: 323714 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3381. Min Act: -0.0001

Data Index: 1288175 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1328560 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3753. Min Act: -0.0001

Data Index: 663989 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3830. Min Act: -0.0001

Data Index: 965574 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3510. Min Act: -0.0001

Data Index: 1011759 (C4 (Web Text))

Max Activating Token Index: 933