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

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

Neuron 5619 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1970. Min Range: -5.1970

Max Act: 5.1970. Min Act: -0.0000

Data Index: 520592 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 5.1970. Min Range: -5.1970

Max Act: 5.1628. Min Act: -0.0000

Data Index: 439642 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 5.1970. Min Range: -5.1970

Max Act: 5.1666. Min Act: -0.0000

Data Index: 1250155 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.9183. Min Act: -0.0000

Data Index: 535923 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.7475. Min Act: -0.0000

Data Index: 1081517 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.6876. Min Act: -0.0000

Data Index: 340494 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.4196. Min Act: -0.0000

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.1803. Min Act: -0.0000

Data Index: 571329 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.2834. Min Act: -0.0000

Data Index: 794530 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 5.1970. Min Range: -5.1970

Max Act: 4.2343. Min Act: -0.0000

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.8748. Min Act: -0.0000

Data Index: 110331 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.7315. Min Act: -0.0000

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.4914. Min Act: -0.0000

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.3999. Min Act: -0.0000

Data Index: 760568 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.4704. Min Act: -0.0000

Data Index: 743564 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.3224. Min Act: -0.0000

Data Index: 467590 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.2017. Min Act: 0.0000

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.1887. Min Act: 0.0000

Data Index: 1019569 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 5.1970. Min Range: -5.1970

Max Act: 3.0452. Min Act: -0.0000

Data Index: 253505 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 5.1970. Min Range: -5.1970

Max Act: 2.8907. Min Act: -0.0000

Data Index: 293941 (C4 (Web Text))

Max Activating Token Index: 159