Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2380 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0594. Min Range: -3.0594

Max Act: 3.0594. Min Act: -0.0001

Data Index: 332563 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.1796. Min Act: -0.0001

Data Index: 605334 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.5432. Min Act: -0.0001

Data Index: 196184 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.9940. Min Act: -0.0001

Data Index: 622249 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.0897. Min Act: -0.0001

Data Index: 824199 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.0573. Min Act: -0.0001

Data Index: 182193 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.2651. Min Act: -0.0001

Data Index: 1126514 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.0113. Min Act: -0.0001

Data Index: 863500 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.8784. Min Act: -0.0001

Data Index: 279219 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.9852. Min Act: -0.0001

Data Index: 1032212 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 3.0594. Min Range: -3.0594

Max Act: 2.0247. Min Act: -0.0001

Data Index: 64261 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.7948. Min Act: -0.0001

Data Index: 107936 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.7960. Min Act: -0.0001

Data Index: 349779 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.6491. Min Act: -0.0001

Data Index: 861076 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.4739. Min Act: -0.0001

Data Index: 116500 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.5775. Min Act: -0.0001

Data Index: 1272113 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.5272. Min Act: -0.0001

Data Index: 559478 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.5999. Min Act: -0.0001

Data Index: 250264 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.5100. Min Act: -0.0001

Data Index: 721825 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.0594. Min Range: -3.0594

Max Act: 1.3887. Min Act: -0.0001

Data Index: 470752 (C4 (Web Text))

Max Activating Token Index: 573