Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 44 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6587. Min Act: -0.0000

Data Index: 586283 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7206. Min Act: -0.0001

Data Index: 1374965 (Python Code)

Max Activating Token Index: 207

Text #2

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7014. Min Act: -0.0001

Data Index: 1542211 (Python Code)

Max Activating Token Index: 369

Text #3

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.7472. Min Act: -0.0001

Data Index: 819234 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5915. Min Act: -0.0001

Data Index: 822365 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1471902 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5577. Min Act: -0.0001

Data Index: 1603593 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1495568 (Python Code)

Max Activating Token Index: 214

Text #8

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5670. Min Act: -0.0001

Data Index: 1461369 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5414. Min Act: -0.0000

Data Index: 982099 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4916. Min Act: -0.0000

Data Index: 184673 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5931. Min Act: -0.0001

Data Index: 1434688 (Python Code)

Max Activating Token Index: 241

Text #12

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5020. Min Act: -0.0001

Data Index: 766990 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1347534 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5339. Min Act: -0.0001

Data Index: 1440356 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5787. Min Act: -0.0001

Data Index: 721130 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1448774 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1302482 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1146762 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1398482 (Python Code)

Max Activating Token Index: 482