Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1494. Min Act: -0.0000

Data Index: 375507 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1340035 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1122118 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0944. Min Act: -0.0001

Data Index: 486256 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1614. Min Act: -0.0000

Data Index: 895726 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9968. Min Act: -0.0000

Data Index: 16931 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1136121 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9538. Min Act: -0.0000

Data Index: 801581 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1095102 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9371. Min Act: -0.0000

Data Index: 726594 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9597. Min Act: -0.0000

Data Index: 56074 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9928. Min Act: -0.0000

Data Index: 289733 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1328876 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9197. Min Act: -0.0000

Data Index: 820897 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1029177 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1168591 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9758. Min Act: -0.0000

Data Index: 974209 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8795. Min Act: -0.0000

Data Index: 928596 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9107. Min Act: -0.0000

Data Index: 469367 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.8915. Min Act: -0.0000

Data Index: 916772 (C4 (Web Text))

Max Activating Token Index: 190