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

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

Neuron 2958 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.9614. Min Act: -0.0000

Data Index: 41498 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1178065 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1065258 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.9007. Min Act: -0.0000

Data Index: 557632 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.8425. Min Act: -0.0000

Data Index: 344875 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.8272. Min Act: 0.0000

Data Index: 813485 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1112638 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.8192. Min Act: -0.0000

Data Index: 187346 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.7674. Min Act: -0.0000

Data Index: 853109 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.7188. Min Act: -0.0000

Data Index: 982048 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6847. Min Act: -0.0000

Data Index: 634566 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6739. Min Act: -0.0000

Data Index: 423151 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1048667 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6616. Min Act: -0.0000

Data Index: 208621 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6788. Min Act: -0.0000

Data Index: 44121 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1255092 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1209130 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6454. Min Act: -0.0000

Data Index: 399479 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6359. Min Act: -0.0000

Data Index: 890477 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.9614. Min Range: -0.9614

Max Act: 0.6287. Min Act: -0.0000

Data Index: 358127 (C4 (Web Text))

Max Activating Token Index: 171