Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 60 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0871. Min Range: -1.0871

Max Act: 1.0871. Min Act: -0.0001

Data Index: 1340619 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9751. Min Act: -0.0001

Data Index: 738562 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9761. Min Act: -0.0001

Data Index: 125365 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9315. Min Act: -0.0001

Data Index: 1014255 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9150. Min Act: -0.0001

Data Index: 406103 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8845. Min Act: -0.0001

Data Index: 850020 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8485. Min Act: -0.0001

Data Index: 1076764 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.9285. Min Act: -0.0001

Data Index: 1221069 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8339. Min Act: -0.0001

Data Index: 403035 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8860. Min Act: -0.0001

Data Index: 187866 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8520. Min Act: -0.0001

Data Index: 775093 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.7975. Min Act: -0.0001

Data Index: 1037856 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.7960. Min Act: -0.0001

Data Index: 981172 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.7770. Min Act: -0.0001

Data Index: 701019 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8205. Min Act: -0.0001

Data Index: 357528 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.7696. Min Act: -0.0001

Data Index: 748063 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8184. Min Act: -0.0001

Data Index: 1191632 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1055418 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1242130 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.0871. Min Range: -1.0871

Max Act: 0.7332. Min Act: -0.0001

Data Index: 1023255 (C4 (Web Text))

Max Activating Token Index: 306