Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.3484. Min Act: -0.0000

Data Index: 272232 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 4.3484. Min Range: -4.3484

Max Act: 4.1970. Min Act: -0.0000

Data Index: 1221789 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.9590. Min Act: -0.0000

Data Index: 931570 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.8678. Min Act: -0.0001

Data Index: 928175 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.6324. Min Act: -0.0001

Data Index: 378227 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.4257. Min Act: -0.0000

Data Index: 1200154 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.7713. Min Act: -0.0001

Data Index: 205252 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.5059. Min Act: -0.0000

Data Index: 1189252 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.5808. Min Act: -0.0001

Data Index: 792575 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.2642. Min Act: -0.0001

Data Index: 355463 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.1771. Min Act: -0.0000

Data Index: 388936 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.2035. Min Act: -0.0001

Data Index: 112958 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.1533. Min Act: -0.0000

Data Index: 102119 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 4.3484. Min Range: -4.3484

Max Act: 2.7852. Min Act: -0.0001

Data Index: 2304 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.0687. Min Act: -0.0001

Data Index: 403341 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 4.3484. Min Range: -4.3484

Max Act: 2.8973. Min Act: -0.0000

Data Index: 1016702 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 4.3484. Min Range: -4.3484

Max Act: 2.8771. Min Act: -0.0000

Data Index: 588487 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.0693. Min Act: -0.0001

Data Index: 3454 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 4.3484. Min Range: -4.3484

Max Act: 2.8537. Min Act: -0.0001

Data Index: 584462 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 4.3484. Min Range: -4.3484

Max Act: 3.0162. Min Act: -0.0000

Data Index: 36694 (C4 (Web Text))

Max Activating Token Index: 756