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

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

Neuron 3776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0662. Min Range: -2.0662

Max Act: 2.0662. Min Act: -0.0000

Data Index: 195296 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.9089. Min Act: -0.0000

Data Index: 133970 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.7875. Min Act: -0.0000

Data Index: 1173356 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.8682. Min Act: -0.0000

Data Index: 322392 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.8462. Min Act: -0.0000

Data Index: 26645 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.7952. Min Act: -0.0000

Data Index: 862699 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.6398. Min Act: -0.0000

Data Index: 1643396 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1485669 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.5344. Min Act: -0.0000

Data Index: 734355 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.7360. Min Act: -0.0000

Data Index: 936823 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.5297. Min Act: -0.0000

Data Index: 415417 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.4158. Min Act: -0.0000

Data Index: 301489 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.4960. Min Act: -0.0000

Data Index: 478855 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.4847. Min Act: -0.0000

Data Index: 195008 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.5500. Min Act: -0.0000

Data Index: 1156803 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.4451. Min Act: -0.0000

Data Index: 898938 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.4205. Min Act: -0.0000

Data Index: 254981 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1249223 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.3750. Min Act: -0.0000

Data Index: 729387 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 2.0662. Min Range: -2.0662

Max Act: 1.2786. Min Act: -0.0000

Data Index: 1143636 (C4 (Web Text))

Max Activating Token Index: 757