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

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

Neuron 1637 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: 1.1516. Min Range: -1.1516

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1325614 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.1440. Min Act: -0.0000

Data Index: 663772 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.1307. Min Act: -0.0000

Data Index: 25275 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.1516. Min Act: -0.0000

Data Index: 524289 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0457. Min Act: -0.0000

Data Index: 225811 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0748. Min Act: -0.0000

Data Index: 271148 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0743. Min Act: -0.0000

Data Index: 990803 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0277. Min Act: 0.0000

Data Index: 520329 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1347234 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0433. Min Act: -0.0000

Data Index: 350941 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1189289 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9748. Min Act: -0.0000

Data Index: 747401 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 1.1516. Min Range: -1.1516

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9703. Min Act: -0.0000

Data Index: 365165 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9216. Min Act: 0.0000

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9484. Min Act: 0.0000

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9489. Min Act: -0.0000

Data Index: 275792 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1350934 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.8731. Min Act: -0.0000

Data Index: 309705 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.1516. Min Range: -1.1516

Max Act: 0.8760. Min Act: -0.0000

Data Index: 964454 (C4 (Web Text))

Max Activating Token Index: 334