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

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

Neuron 2652 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1655671 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1295. Min Act: -0.0000

Data Index: 142374 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1529881 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1117. Min Act: -0.0000

Data Index: 427810 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1064220 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1088. Min Act: -0.0000

Data Index: 603934 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1454278 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1128882 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1018. Min Act: -0.0000

Data Index: 915958 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1635055 (Python Code)

Max Activating Token Index: 1007

Text #10

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0996. Min Act: -0.0000

Data Index: 959447 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1592476 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0907. Min Act: -0.0000

Data Index: 59555 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1062. Min Act: -0.0000

Data Index: 895251 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0982. Min Act: -0.0000

Data Index: 331353 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0853. Min Act: -0.0000

Data Index: 790937 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1446693 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1218610 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0945. Min Act: -0.0000

Data Index: 693029 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0922. Min Act: -0.0000

Data Index: 561304 (C4 (Web Text))

Max Activating Token Index: 878