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

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

Neuron 298 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.9528. Min Act: -0.0000

Data Index: 517637 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7981. Min Act: -0.0000

Data Index: 307545 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7327. Min Act: -0.0000

Data Index: 455942 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7320. Min Act: -0.0000

Data Index: 474591 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1325774 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7131. Min Act: -0.0000

Data Index: 786062 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.6754. Min Act: -0.0000

Data Index: 490844 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7324. Min Act: -0.0000

Data Index: 193323 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.7012. Min Act: -0.0000

Data Index: 143567 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.6538. Min Act: -0.0000

Data Index: 436465 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1309088 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.6047. Min Act: -0.0000

Data Index: 943807 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5847. Min Act: -0.0000

Data Index: 787694 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5935. Min Act: -0.0000

Data Index: 504864 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1148211 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5342. Min Act: -0.0000

Data Index: 620179 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1021515 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5074. Min Act: -0.0000

Data Index: 670079 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5531. Min Act: -0.0000

Data Index: 782368 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.9528. Min Range: -0.9528

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1343504 (C4 (Web Text))

Max Activating Token Index: 315