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

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

Neuron 1154 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0771. Min Range: -2.0771

Max Act: 2.0771. Min Act: -0.0000

Data Index: 359862 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.9416. Min Act: -0.0000

Data Index: 256570 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.6656. Min Act: -0.0000

Data Index: 96263 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.6980. Min Act: -0.0000

Data Index: 1194635 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.4806. Min Act: -0.0000

Data Index: 1398521 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3322. Min Act: -0.0000

Data Index: 802127 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.5028. Min Act: -0.0000

Data Index: 896195 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.4390. Min Act: -0.0000

Data Index: 506950 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.5377. Min Act: -0.0000

Data Index: 1439440 (Python Code)

Max Activating Token Index: 161

Text #9

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1496569 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.4012. Min Act: -0.0000

Data Index: 286606 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1433690 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1479790 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3998. Min Act: -0.0000

Data Index: 817994 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3394. Min Act: -0.0000

Data Index: 770114 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3687. Min Act: -0.0000

Data Index: 647791 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1351053 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3010. Min Act: -0.0000

Data Index: 551041 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.3266. Min Act: -0.0000

Data Index: 121324 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 2.0771. Min Range: -2.0771

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1301696 (C4 (Web Text))

Max Activating Token Index: 63