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

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

Neuron 4815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5203. Min Range: -8.5203

Max Act: 8.5203. Min Act: -0.0000

Data Index: 775406 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 8.5203. Min Range: -8.5203

Max Act: 7.5152. Min Act: -0.0000

Data Index: 1298769 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 8.5203. Min Range: -8.5203

Max Act: 7.5863. Min Act: -0.0000

Data Index: 11308 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 8.5203. Min Range: -8.5203

Max Act: 7.1088. Min Act: -0.0000

Data Index: 1076285 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.5181. Min Act: -0.0000

Data Index: 864629 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 8.5203. Min Range: -8.5203

Max Act: 7.0307. Min Act: -0.0000

Data Index: 1300175 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.9726. Min Act: -0.0001

Data Index: 988556 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 8.5203. Min Range: -8.5203

Max Act: 5.9156. Min Act: -0.0000

Data Index: 679164 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.4371. Min Act: -0.0000

Data Index: 868070 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.4814. Min Act: -0.0000

Data Index: 152075 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.4551. Min Act: -0.0001

Data Index: 775518 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 8.5203. Min Range: -8.5203

Max Act: 5.6932. Min Act: -0.0000

Data Index: 34588 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.5814. Min Act: -0.0001

Data Index: 994468 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 8.5203. Min Range: -8.5203

Max Act: 5.8429. Min Act: -0.0000

Data Index: 761439 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.1988. Min Act: -0.0000

Data Index: 476915 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 8.5203. Min Range: -8.5203

Max Act: 5.9496. Min Act: -0.0000

Data Index: 494597 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.1331. Min Act: -0.0000

Data Index: 20771 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 8.5203. Min Range: -8.5203

Max Act: 5.3797. Min Act: -0.0000

Data Index: 1098060 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 8.5203. Min Range: -8.5203

Max Act: 5.3844. Min Act: -0.0001

Data Index: 44972 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 8.5203. Min Range: -8.5203

Max Act: 6.6235. Min Act: -0.0000

Data Index: 284635 (C4 (Web Text))

Max Activating Token Index: 345