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

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

Neuron 4980 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: 0.9474. Min Range: -0.9474

Max Act: 0.9474. Min Act: -0.0000

Data Index: 594899 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1348253 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6986. Min Act: -0.0000

Data Index: 188333 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1156966 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6289. Min Act: -0.0000

Data Index: 962870 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1174654 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1098750 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6307. Min Act: -0.0000

Data Index: 938054 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6367. Min Act: -0.0000

Data Index: 838400 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6611. Min Act: -0.0000

Data Index: 603369 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6370. Min Act: -0.0000

Data Index: 642600 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6436. Min Act: -0.0000

Data Index: 926826 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.5572. Min Act: -0.0000

Data Index: 71673 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1324624 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.5782. Min Act: -0.0000

Data Index: 836664 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1159978 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1024138 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.6054. Min Act: -0.0000

Data Index: 220443 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.5739. Min Act: -0.0000

Data Index: 673839 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.9474. Min Range: -0.9474

Max Act: 0.5520. Min Act: -0.0000

Data Index: 835238 (C4 (Web Text))

Max Activating Token Index: 830