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

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

Neuron 4513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.7357. Min Act: -0.0000

Data Index: 932605 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.7344. Min Act: -0.0000

Data Index: 376431 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.6284. Min Act: -0.0000

Data Index: 1353793 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.5822. Min Act: -0.0000

Data Index: 32503 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.5738. Min Act: -0.0000

Data Index: 51297 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.7446. Min Act: -0.0000

Data Index: 464962 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3721. Min Act: -0.0000

Data Index: 867575 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.5337. Min Act: -0.0000

Data Index: 1331384 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.7200. Min Act: -0.0000

Data Index: 282119 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.5111. Min Act: -0.0000

Data Index: 586597 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3311. Min Act: -0.0000

Data Index: 870954 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.6775. Min Act: -0.0000

Data Index: 397282 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.4568. Min Act: -0.0000

Data Index: 1128400 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3993. Min Act: -0.0000

Data Index: 12685 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3940. Min Act: -0.0000

Data Index: 1101531 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3931. Min Act: -0.0000

Data Index: 61467 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.5752. Min Act: -0.0000

Data Index: 1045220 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.2092. Min Act: -0.0000

Data Index: 1137935 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3759. Min Act: -0.0000

Data Index: 509480 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 4.7446. Min Range: -4.7446

Max Act: 4.3711. Min Act: -0.0000

Data Index: 433999 (C4 (Web Text))

Max Activating Token Index: 708