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

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

Neuron 2183 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: 1.0909. Min Range: -1.0909

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1527887 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1503648 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1397854 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1401963 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1380799 (Python Code)

Max Activating Token Index: 275

Text #5

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1383413 (Python Code)

Max Activating Token Index: 378

Text #6

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1409145 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1589062 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1457292 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1427924 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1490967 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1417396 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.8018. Min Act: -0.0001

Data Index: 1463524 (Python Code)

Max Activating Token Index: 435

Text #13

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1607664 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1449171 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1518695 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1398363 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1368782 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1485947 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.7382. Min Act: -0.0001

Data Index: 1601598 (Python Code)

Max Activating Token Index: 107