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

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

Neuron 5089 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: 1.8287. Min Range: -1.8287

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1434245 (Python Code)

Max Activating Token Index: 240

Text #1

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.8287. Min Act: -0.0000

Data Index: 181758 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.7309. Min Act: -0.0000

Data Index: 1500223 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.6592. Min Act: -0.0000

Data Index: 166829 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5572. Min Act: -0.0000

Data Index: 492138 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.6501. Min Act: -0.0000

Data Index: 237240 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5933. Min Act: -0.0000

Data Index: 1150544 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.6330. Min Act: -0.0000

Data Index: 1120262 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1606444 (Python Code)

Max Activating Token Index: 786

Text #9

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5865. Min Act: -0.0000

Data Index: 622508 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5256. Min Act: -0.0000

Data Index: 781440 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5867. Min Act: -0.0000

Data Index: 867618 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1462855 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5619. Min Act: -0.0000

Data Index: 513399 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5562. Min Act: -0.0000

Data Index: 690032 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5489. Min Act: -0.0000

Data Index: 71974 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4432. Min Act: -0.0000

Data Index: 1561678 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4190. Min Act: -0.0000

Data Index: 1614975 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4993. Min Act: -0.0000

Data Index: 884197 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4945. Min Act: -0.0000

Data Index: 1013694 (C4 (Web Text))

Max Activating Token Index: 424