Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2338 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1826. Min Act: -0.0001

Data Index: 853515 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1570666 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1381. Min Act: -0.0001

Data Index: 15157 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1239463 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1268. Min Act: -0.0001

Data Index: 129120 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1243. Min Act: -0.0001

Data Index: 899056 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1262. Min Act: -0.0001

Data Index: 887690 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1251. Min Act: -0.0001

Data Index: 107799 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1120. Min Act: -0.0001

Data Index: 983448 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1147. Min Act: -0.0001

Data Index: 427483 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1192. Min Act: -0.0001

Data Index: 799208 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1389965 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1255477 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1145. Min Act: -0.0001

Data Index: 665010 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1331968 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1451220 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.0998. Min Act: -0.0001

Data Index: 597487 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1098. Min Act: -0.0001

Data Index: 394705 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1122. Min Act: -0.0001

Data Index: 747981 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1024. Min Act: -0.0001

Data Index: 849242 (C4 (Web Text))

Max Activating Token Index: 63