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

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

Neuron 88 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7762. Min Range: -4.7762

Max Act: 4.7762. Min Act: -0.0000

Data Index: 1285968 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 4.7762. Min Range: -4.7762

Max Act: 3.4443. Min Act: -0.0000

Data Index: 475470 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 4.7762. Min Range: -4.7762

Max Act: 3.3628. Min Act: -0.0000

Data Index: 442898 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.9101. Min Act: -0.0000

Data Index: 1357417 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 4.7762. Min Range: -4.7762

Max Act: 3.0253. Min Act: -0.0000

Data Index: 974755 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 4.7762. Min Range: -4.7762

Max Act: 3.2010. Min Act: -0.0000

Data Index: 734789 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.8975. Min Act: -0.0000

Data Index: 104842 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.8482. Min Act: -0.0000

Data Index: 1017217 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.7164. Min Act: -0.0000

Data Index: 298142 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.6956. Min Act: -0.0000

Data Index: 540641 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.6804. Min Act: -0.0000

Data Index: 783948 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.5128. Min Act: -0.0000

Data Index: 1055768 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.7387. Min Act: -0.0000

Data Index: 623814 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.5745. Min Act: -0.0000

Data Index: 1257883 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.5815. Min Act: -0.0000

Data Index: 82220 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.4333. Min Act: -0.0000

Data Index: 303219 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.6201. Min Act: -0.0000

Data Index: 1359000 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.4041. Min Act: -0.0000

Data Index: 603825 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.5414. Min Act: -0.0000

Data Index: 438063 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 4.7762. Min Range: -4.7762

Max Act: 2.2867. Min Act: -0.0000

Data Index: 1342073 (C4 (Web Text))

Max Activating Token Index: 413