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

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

Neuron 1583 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: 1.7923. Min Range: -1.7923

Max Act: 1.7923. Min Act: -0.0001

Data Index: 417193 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.7923. Min Range: -1.7923

Max Act: 1.2820. Min Act: -0.0001

Data Index: 337188 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.7923. Min Range: -1.7923

Max Act: 1.2541. Min Act: -0.0001

Data Index: 1341023 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.7923. Min Range: -1.7923

Max Act: 1.2053. Min Act: -0.0001

Data Index: 104278 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 1.7923. Min Range: -1.7923

Max Act: 1.1277. Min Act: -0.0001

Data Index: 1248230 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.7923. Min Range: -1.7923

Max Act: 1.1821. Min Act: -0.0001

Data Index: 657177 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1259104 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8594. Min Act: -0.0001

Data Index: 852034 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1307748 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8070. Min Act: -0.0001

Data Index: 885852 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8200. Min Act: -0.0001

Data Index: 991147 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1098042 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1461795 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7849. Min Act: -0.0001

Data Index: 1060830 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7422. Min Act: -0.0001

Data Index: 556732 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7662. Min Act: -0.0001

Data Index: 1284230 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1129483 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1076440 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.8094. Min Act: -0.0001

Data Index: 104316 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.7923. Min Range: -1.7923

Max Act: 0.7159. Min Act: -0.0000

Data Index: 549288 (C4 (Web Text))

Max Activating Token Index: 601