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

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

Neuron 3339 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.3593. Min Act: -0.0000

Data Index: 691966 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2794. Min Act: -0.0000

Data Index: 724774 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1208. Min Act: -0.0000

Data Index: 645034 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2181. Min Act: -0.0001

Data Index: 175499 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.1667. Min Act: -0.0000

Data Index: 1192646 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.2027. Min Act: -0.0000

Data Index: 367384 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1061737 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0756. Min Act: -0.0001

Data Index: 673697 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0251. Min Act: -0.0000

Data Index: 474283 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1251611 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.3593. Min Range: -1.3593

Max Act: 1.0225. Min Act: -0.0000

Data Index: 552716 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9096. Min Act: -0.0001

Data Index: 1231235 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1079408 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9612. Min Act: -0.0000

Data Index: 762993 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9317. Min Act: -0.0000

Data Index: 318313 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.8848. Min Act: -0.0001

Data Index: 495876 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1228789 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1270917 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.8993. Min Act: -0.0000

Data Index: 821348 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.3593. Min Range: -1.3593

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1076219 (C4 (Web Text))

Max Activating Token Index: 402