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

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

Neuron 3815 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: 1.3010. Min Range: -1.3010

Max Act: 1.3010. Min Act: -0.0001

Data Index: 415194 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.1454. Min Act: -0.0001

Data Index: 1369480 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.1363. Min Act: -0.0001

Data Index: 1431437 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1256235 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0319. Min Act: -0.0001

Data Index: 1617047 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0169. Min Act: -0.0001

Data Index: 1474217 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1494469 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0018. Min Act: -0.0001

Data Index: 1424838 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9696. Min Act: -0.0001

Data Index: 1065766 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0537. Min Act: -0.0001

Data Index: 561385 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9427. Min Act: -0.0001

Data Index: 1259287 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9945. Min Act: -0.0001

Data Index: 1394258 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9440. Min Act: -0.0001

Data Index: 1270885 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9395. Min Act: -0.0001

Data Index: 1366352 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8898. Min Act: -0.0001

Data Index: 1109243 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9464. Min Act: -0.0001

Data Index: 1492652 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8533. Min Act: -0.0001

Data Index: 690207 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8663. Min Act: -0.0001

Data Index: 887155 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1608382 (Python Code)

Max Activating Token Index: 671

Text #19

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8062. Min Act: -0.0001

Data Index: 198398 (C4 (Web Text))

Max Activating Token Index: 112