Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4674 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.9960. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.8554. Min Act: -0.0000

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.6981. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.7936. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.6025. Min Act: -0.0000

Data Index: 864194 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.6363. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.4971. Min Act: -0.0000

Data Index: 1503137 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.5148. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.4260. Min Act: -0.0000

Data Index: 1457118 (Python Code)

Max Activating Token Index: 336

Text #10

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.3589. Min Act: -0.0000

Data Index: 496340 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.3353. Min Act: -0.0000

Data Index: 491379 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1016499 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.2838. Min Act: -0.0000

Data Index: 901147 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.2956. Min Act: -0.0000

Data Index: 17478 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.3083. Min Act: -0.0000

Data Index: 18205 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1245513 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.1945. Min Act: -0.0000

Data Index: 501956 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1572206 (Python Code)

Max Activating Token Index: 984

Text #19

Max Range: 1.9960. Min Range: -1.9960

Max Act: 1.2039. Min Act: -0.0000

Data Index: 499202 (C4 (Web Text))

Max Activating Token Index: 502