Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0691. Min Range: -2.0691

Max Act: 2.0691. Min Act: -0.0000

Data Index: 1052518 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 2.0691. Min Range: -2.0691

Max Act: 2.0463. Min Act: -0.0000

Data Index: 899795 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.8454. Min Act: -0.0000

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.6906. Min Act: -0.0001

Data Index: 832211 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5378. Min Act: -0.0000

Data Index: 144215 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.6202. Min Act: -0.0001

Data Index: 1025964 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.6142. Min Act: -0.0001

Data Index: 1348159 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.7067. Min Act: -0.0001

Data Index: 120247 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.6522. Min Act: -0.0001

Data Index: 611145 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1145007 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1146466 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5385. Min Act: -0.0000

Data Index: 498806 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.4692. Min Act: -0.0000

Data Index: 20853 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5935. Min Act: -0.0001

Data Index: 406957 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5790. Min Act: -0.0000

Data Index: 535073 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.4979. Min Act: -0.0000

Data Index: 519743 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5164. Min Act: -0.0000

Data Index: 655392 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5228. Min Act: -0.0000

Data Index: 985830 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1336677 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 2.0691. Min Range: -2.0691

Max Act: 1.5983. Min Act: -0.0000

Data Index: 882417 (C4 (Web Text))

Max Activating Token Index: 471