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

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

Neuron 1970 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0275. Min Range: -7.0275

Max Act: 7.0275. Min Act: -0.0001

Data Index: 1449135 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.9482. Min Act: -0.0001

Data Index: 1400020 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.8309. Min Act: -0.0001

Data Index: 1649790 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.7525. Min Act: -0.0001

Data Index: 1640815 (Python Code)

Max Activating Token Index: 893

Text #4

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.5591. Min Act: -0.0001

Data Index: 1624866 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.6867. Min Act: -0.0001

Data Index: 1486838 (Python Code)

Max Activating Token Index: 599

Text #6

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.5254. Min Act: -0.0001

Data Index: 1396006 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.4012. Min Act: -0.0001

Data Index: 1423798 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.3605. Min Act: -0.0001

Data Index: 1411790 (Python Code)

Max Activating Token Index: 482

Text #9

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.3136. Min Act: -0.0001

Data Index: 1432029 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.3140. Min Act: -0.0001

Data Index: 1536110 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 7.0275. Min Range: -7.0275

Max Act: 5.9736. Min Act: -0.0001

Data Index: 1473289 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 7.0275. Min Range: -7.0275

Max Act: 5.9734. Min Act: -0.0001

Data Index: 1652849 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.2871. Min Act: -0.0001

Data Index: 1473637 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 7.0275. Min Range: -7.0275

Max Act: 5.8547. Min Act: -0.0001

Data Index: 1505429 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.0375. Min Act: -0.0001

Data Index: 1615996 (Python Code)

Max Activating Token Index: 989

Text #16

Max Range: 7.0275. Min Range: -7.0275

Max Act: 6.2131. Min Act: -0.0001

Data Index: 1526809 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 7.0275. Min Range: -7.0275

Max Act: 5.9354. Min Act: -0.0001

Data Index: 1373986 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 7.0275. Min Range: -7.0275

Max Act: 5.8953. Min Act: -0.0001

Data Index: 1649842 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 7.0275. Min Range: -7.0275

Max Act: 5.8900. Min Act: -0.0001

Data Index: 1403256 (Python Code)

Max Activating Token Index: 229