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

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

Neuron 2146 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: 0.8345. Min Range: -0.8345

Max Act: 0.8195. Min Act: -0.0001

Data Index: 804732 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.8345. Min Act: -0.0001

Data Index: 167809 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7955. Min Act: -0.0001

Data Index: 408979 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1128001 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7668. Min Act: -0.0001

Data Index: 1101158 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7604. Min Act: -0.0001

Data Index: 79948 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7448. Min Act: -0.0001

Data Index: 117513 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7305. Min Act: -0.0001

Data Index: 497895 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7293. Min Act: -0.0001

Data Index: 717197 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7296. Min Act: -0.0001

Data Index: 5073 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6890. Min Act: -0.0001

Data Index: 325593 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.7098. Min Act: -0.0001

Data Index: 127592 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6708. Min Act: -0.0001

Data Index: 344525 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6641. Min Act: -0.0001

Data Index: 647306 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6820. Min Act: -0.0001

Data Index: 987796 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6765. Min Act: -0.0001

Data Index: 987721 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6790. Min Act: -0.0001

Data Index: 109524 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6459. Min Act: -0.0001

Data Index: 426204 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6433. Min Act: -0.0001

Data Index: 683175 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.8345. Min Range: -0.8345

Max Act: 0.6619. Min Act: -0.0001

Data Index: 1181287 (C4 (Web Text))

Max Activating Token Index: 246