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

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

Neuron 2125 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4525. Min Act: -0.0001

Data Index: 960511 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1203738 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4594. Min Act: -0.0001

Data Index: 935951 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4049. Min Act: -0.0001

Data Index: 42077 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1061068 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3904. Min Act: -0.0001

Data Index: 300490 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3842. Min Act: -0.0001

Data Index: 892513 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3844. Min Act: -0.0001

Data Index: 325061 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3977. Min Act: -0.0001

Data Index: 176813 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3475. Min Act: -0.0001

Data Index: 1134460 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3386. Min Act: -0.0001

Data Index: 1050311 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3390. Min Act: -0.0001

Data Index: 429436 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3586. Min Act: -0.0001

Data Index: 764845 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1028464 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3656. Min Act: -0.0001

Data Index: 354681 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3754. Min Act: -0.0001

Data Index: 459954 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4010. Min Act: -0.0001

Data Index: 764160 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3624. Min Act: -0.0001

Data Index: 217622 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.2978. Min Act: -0.0001

Data Index: 122359 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1142607 (C4 (Web Text))

Max Activating Token Index: 749