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

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

Neuron 4832 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.4014. Min Act: -0.0001

Data Index: 385555 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3572. Min Act: -0.0001

Data Index: 977664 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3002. Min Act: -0.0001

Data Index: 142289 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0231. Min Act: -0.0001

Data Index: 747305 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1819. Min Act: -0.0001

Data Index: 661425 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1508. Min Act: -0.0001

Data Index: 1251275 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1036. Min Act: -0.0001

Data Index: 348202 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1330. Min Act: -0.0001

Data Index: 616888 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0142. Min Act: -0.0001

Data Index: 251989 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.9936. Min Act: -0.0001

Data Index: 699934 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0606. Min Act: -0.0001

Data Index: 594470 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0059. Min Act: -0.0001

Data Index: 1177339 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0637. Min Act: -0.0001

Data Index: 281436 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0163. Min Act: -0.0001

Data Index: 539941 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0312. Min Act: -0.0001

Data Index: 139503 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0310. Min Act: -0.0001

Data Index: 1044912 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0101. Min Act: -0.0001

Data Index: 819622 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.9424. Min Act: -0.0001

Data Index: 74369 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1217100 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.4014. Min Range: -1.4014

Max Act: 0.9530. Min Act: -0.0001

Data Index: 99160 (C4 (Web Text))

Max Activating Token Index: 801