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

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

Neuron 4512 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: 1.9133. Min Range: -1.9133

Max Act: 1.9133. Min Act: -0.0001

Data Index: 106558 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.7816. Min Act: -0.0001

Data Index: 1256690 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.5458. Min Act: -0.0001

Data Index: 850208 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3552. Min Act: -0.0000

Data Index: 357217 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3992. Min Act: -0.0000

Data Index: 991733 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3720. Min Act: -0.0000

Data Index: 107225 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2144. Min Act: -0.0001

Data Index: 375727 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2922. Min Act: -0.0001

Data Index: 905905 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2081. Min Act: -0.0000

Data Index: 98292 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.3728. Min Act: -0.0001

Data Index: 1119043 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1588. Min Act: -0.0000

Data Index: 796672 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1336. Min Act: -0.0000

Data Index: 988811 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1102662 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2521. Min Act: -0.0001

Data Index: 1506233 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1601. Min Act: -0.0000

Data Index: 1384313 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1048202 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1753. Min Act: -0.0001

Data Index: 456609 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.0624. Min Act: -0.0001

Data Index: 84175 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.1429. Min Act: -0.0000

Data Index: 1133022 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.9133. Min Range: -1.9133

Max Act: 1.2128. Min Act: -0.0001

Data Index: 447595 (C4 (Web Text))

Max Activating Token Index: 652