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

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

Neuron 4235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1019498 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1547312 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1241308 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1630319 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1578436 (Python Code)

Max Activating Token Index: 120

Text #5

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1184213 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1492752 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1515321 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1534265 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5443. Min Act: -0.0001

Data Index: 1603414 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1529905 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1577158 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1495004 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1618406 (Python Code)

Max Activating Token Index: 500

Text #14

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5553. Min Act: -0.0000

Data Index: 951084 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1412329 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.4940. Min Act: -0.0000

Data Index: 720276 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.6288. Min Act: -0.0000

Data Index: 361384 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1387383 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 0.7342. Min Range: -0.7342

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1537294 (Python Code)

Max Activating Token Index: 49