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

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

Neuron 2951 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0295. Min Range: -2.0295

Max Act: 2.0295. Min Act: -0.0000

Data Index: 219513 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.9943. Min Act: -0.0000

Data Index: 227697 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.6335. Min Act: -0.0000

Data Index: 191080 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1166996 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1261496 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.5008. Min Act: -0.0000

Data Index: 432312 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1174239 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1114177 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.4549. Min Act: -0.0000

Data Index: 813083 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.3647. Min Act: -0.0000

Data Index: 839864 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.2922. Min Act: -0.0000

Data Index: 318258 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.3692. Min Act: -0.0000

Data Index: 351563 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.3532. Min Act: -0.0000

Data Index: 700162 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.4426. Min Act: -0.0000

Data Index: 1275912 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.3986. Min Act: -0.0000

Data Index: 929717 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.2589. Min Act: -0.0000

Data Index: 671183 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.4104. Min Act: -0.0000

Data Index: 101064 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1025628 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 2.0295. Min Range: -2.0295

Max Act: 1.4109. Min Act: -0.0000

Data Index: 628185 (C4 (Web Text))

Max Activating Token Index: 731