Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1572263 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1409456 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1517848 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1602012 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1432260 (Python Code)

Max Activating Token Index: 954

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1383673 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1218. Min Act: -0.0001

Data Index: 40990 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1393485 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1614942 (Python Code)

Max Activating Token Index: 1001

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1360383 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1546179 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1054. Min Act: -0.0001

Data Index: 852656 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1608306 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1512382 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1461013 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1605589 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1612018 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1562158 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1396902 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0921. Min Act: -0.0001

Data Index: 697457 (C4 (Web Text))

Max Activating Token Index: 468