Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1594 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.4636. Min Act: -0.0001

Data Index: 538848 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2147. Min Act: -0.0001

Data Index: 1294159 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1781. Min Act: -0.0001

Data Index: 52489 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.3682. Min Act: -0.0001

Data Index: 645675 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.2066. Min Act: -0.0001

Data Index: 1014979 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0222. Min Act: -0.0001

Data Index: 77829 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0950. Min Act: -0.0001

Data Index: 1209512 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1113. Min Act: -0.0001

Data Index: 108225 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.1748. Min Act: -0.0001

Data Index: 523790 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0775. Min Act: -0.0001

Data Index: 698246 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0050. Min Act: -0.0001

Data Index: 964979 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0026. Min Act: -0.0001

Data Index: 587499 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9995. Min Act: -0.0001

Data Index: 137358 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0151. Min Act: -0.0001

Data Index: 1227915 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0349. Min Act: -0.0001

Data Index: 1280191 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9628. Min Act: -0.0001

Data Index: 166347 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9529. Min Act: -0.0001

Data Index: 592021 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 1.4636. Min Range: -1.4636

Max Act: 1.0484. Min Act: -0.0001

Data Index: 530792 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9314. Min Act: -0.0001

Data Index: 993148 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.4636. Min Range: -1.4636

Max Act: 0.9024. Min Act: -0.0001

Data Index: 1245561 (C4 (Web Text))

Max Activating Token Index: 662