Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3549 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7593. Min Range: -3.7593

Max Act: 3.7593. Min Act: -0.0000

Data Index: 995110 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.7593. Min Range: -3.7593

Max Act: 3.6491. Min Act: -0.0000

Data Index: 580037 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 3.7593. Min Range: -3.7593

Max Act: 3.5900. Min Act: -0.0000

Data Index: 805018 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.7593. Min Range: -3.7593

Max Act: 3.3591. Min Act: -0.0000

Data Index: 332950 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 3.7593. Min Range: -3.7593

Max Act: 3.0059. Min Act: -0.0000

Data Index: 163312 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 3.7593. Min Range: -3.7593

Max Act: 3.2480. Min Act: -0.0000

Data Index: 973572 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.8526. Min Act: -0.0000

Data Index: 138241 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.7999. Min Act: -0.0000

Data Index: 512159 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.7992. Min Act: -0.0000

Data Index: 36210 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.6817. Min Act: -0.0000

Data Index: 884727 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.8149. Min Act: -0.0000

Data Index: 708990 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.8015. Min Act: -0.0000

Data Index: 503832 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.7822. Min Act: -0.0000

Data Index: 973352 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.7802. Min Act: -0.0000

Data Index: 918080 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.5800. Min Act: -0.0000

Data Index: 653316 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.4539. Min Act: -0.0000

Data Index: 379500 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.7933. Min Act: -0.0000

Data Index: 1289988 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.5056. Min Act: -0.0000

Data Index: 1192408 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.3387. Min Act: -0.0001

Data Index: 748818 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 3.7593. Min Range: -3.7593

Max Act: 2.5677. Min Act: -0.0000

Data Index: 1240589 (C4 (Web Text))

Max Activating Token Index: 418