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

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

Neuron 2616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3597. Min Range: -1.3597

Max Act: 1.3597. Min Act: -0.0001

Data Index: 526830 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.3597. Min Range: -1.3597

Max Act: 1.0030. Min Act: -0.0001

Data Index: 736536 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9883. Min Act: -0.0001

Data Index: 1196868 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1097747 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.3597. Min Range: -1.3597

Max Act: 1.0129. Min Act: -0.0001

Data Index: 1055482 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8849. Min Act: -0.0001

Data Index: 453219 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9030. Min Act: -0.0001

Data Index: 87382 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8457. Min Act: -0.0001

Data Index: 214765 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9672. Min Act: -0.0001

Data Index: 203782 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9065. Min Act: -0.0001

Data Index: 620468 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.3597. Min Range: -1.3597

Max Act: 1.0161. Min Act: -0.0001

Data Index: 1029855 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8919. Min Act: -0.0001

Data Index: 304792 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8147. Min Act: -0.0001

Data Index: 1318055 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8690. Min Act: -0.0001

Data Index: 1218500 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8388. Min Act: -0.0001

Data Index: 1241532 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8873. Min Act: -0.0001

Data Index: 981480 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9596. Min Act: -0.0001

Data Index: 882712 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9059. Min Act: -0.0001

Data Index: 1038726 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.8526. Min Act: -0.0001

Data Index: 1321347 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 1.3597. Min Range: -1.3597

Max Act: 0.9032. Min Act: -0.0001

Data Index: 1349231 (C4 (Web Text))

Max Activating Token Index: 890