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

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

Neuron 161 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1611392 (Python Code)

Max Activating Token Index: 905

Text #1

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1422442 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1645394 (Python Code)

Max Activating Token Index: 779

Text #3

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1631299 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1402333 (Python Code)

Max Activating Token Index: 201

Text #5

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1417162 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6955. Min Act: -0.0000

Data Index: 269144 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1442570 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1612505 (Python Code)

Max Activating Token Index: 659

Text #9

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1496682 (Python Code)

Max Activating Token Index: 428

Text #10

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1598200 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1623700 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1627487 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1422428 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1532849 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1619848 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.6241. Min Act: -0.0000

Data Index: 662451 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1474877 (Python Code)

Max Activating Token Index: 363

Text #18

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1615925 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 0.8708. Min Range: -0.8708

Max Act: 0.5773. Min Act: -0.0000

Data Index: 345923 (C4 (Web Text))

Max Activating Token Index: 253