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

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

Neuron 800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5960. Min Act: -0.0000

Data Index: 973440 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5874. Min Act: -0.0000

Data Index: 999490 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5345. Min Act: -0.0000

Data Index: 159896 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1208870 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5372. Min Act: -0.0000

Data Index: 374187 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4855. Min Act: -0.0000

Data Index: 50810 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4658. Min Act: -0.0000

Data Index: 934990 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4730. Min Act: -0.0000

Data Index: 917428 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4400. Min Act: -0.0000

Data Index: 110647 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4495. Min Act: -0.0000

Data Index: 649060 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4486. Min Act: -0.0000

Data Index: 791559 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4347. Min Act: -0.0000

Data Index: 277954 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1070705 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1180948 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1333503 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4133. Min Act: -0.0000

Data Index: 430666 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1116196 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1283033 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3831. Min Act: -0.0000

Data Index: 726125 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.3902. Min Act: -0.0000

Data Index: 341411 (C4 (Web Text))

Max Activating Token Index: 570