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

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

Neuron 1819 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3743. Min Range: -3.3743

Max Act: 3.3743. Min Act: -0.0000

Data Index: 1332169 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 3.3743. Min Range: -3.3743

Max Act: 3.1464. Min Act: -0.0001

Data Index: 991263 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.3743. Min Range: -3.3743

Max Act: 3.3010. Min Act: -0.0000

Data Index: 801367 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 3.3743. Min Range: -3.3743

Max Act: 3.2207. Min Act: -0.0000

Data Index: 987287 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 3.3743. Min Range: -3.3743

Max Act: 3.0242. Min Act: -0.0000

Data Index: 998772 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.5607. Min Act: -0.0000

Data Index: 535903 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.7543. Min Act: -0.0000

Data Index: 886569 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.6542. Min Act: -0.0001

Data Index: 27464 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.5672. Min Act: -0.0001

Data Index: 274239 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.5565. Min Act: -0.0000

Data Index: 953606 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.6443. Min Act: -0.0001

Data Index: 727656 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.3754. Min Act: -0.0000

Data Index: 1139985 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.3649. Min Act: -0.0000

Data Index: 793212 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.7367. Min Act: -0.0001

Data Index: 597915 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.3188. Min Act: -0.0001

Data Index: 1044067 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.5218. Min Act: -0.0000

Data Index: 127922 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.4204. Min Act: -0.0000

Data Index: 914640 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.2985. Min Act: -0.0000

Data Index: 185953 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.5388. Min Act: -0.0000

Data Index: 1108824 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.3743. Min Range: -3.3743

Max Act: 2.2924. Min Act: -0.0000

Data Index: 1189023 (C4 (Web Text))

Max Activating Token Index: 22