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

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

Neuron 5986 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1301. Min Range: -1.1301

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1494203 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 1.1301. Min Range: -1.1301

Max Act: 1.0666. Min Act: -0.0000

Data Index: 213613 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.1301. Min Range: -1.1301

Max Act: 1.1301. Min Act: -0.0000

Data Index: 736747 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.1301. Min Range: -1.1301

Max Act: 1.0423. Min Act: -0.0000

Data Index: 602895 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9410. Min Act: -0.0000

Data Index: 468046 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1586533 (Python Code)

Max Activating Token Index: 764

Text #6

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9265. Min Act: -0.0000

Data Index: 709650 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9255. Min Act: -0.0000

Data Index: 157840 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1312407 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1179050 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9084. Min Act: -0.0000

Data Index: 403731 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8914. Min Act: -0.0000

Data Index: 330723 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8875. Min Act: -0.0000

Data Index: 770672 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1646726 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8515. Min Act: -0.0000

Data Index: 368968 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1080635 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1171838 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1098133 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8371. Min Act: -0.0000

Data Index: 437195 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8399. Min Act: -0.0000

Data Index: 777247 (C4 (Web Text))

Max Activating Token Index: 647