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

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

Neuron 5793 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: 1.6740. Min Range: -1.6740

Max Act: 1.6740. Min Act: -0.0000

Data Index: 389681 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.6256. Min Act: -0.0000

Data Index: 224260 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1434610 (Python Code)

Max Activating Token Index: 1010

Text #3

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.1666. Min Act: -0.0000

Data Index: 720994 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1295057 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1516233 (Python Code)

Max Activating Token Index: 793

Text #6

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.0358. Min Act: -0.0000

Data Index: 701538 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.6740. Min Range: -1.6740

Max Act: 1.0707. Min Act: -0.0000

Data Index: 71550 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1588228 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1430091 (Python Code)

Max Activating Token Index: 616

Text #10

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1196643 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1553815 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1543120 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1530706 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.8564. Min Act: -0.0000

Data Index: 414194 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.8454. Min Act: -0.0000

Data Index: 364363 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1031867 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.7983. Min Act: -0.0000

Data Index: 934317 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1560484 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 1.6740. Min Range: -1.6740

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1486778 (Python Code)

Max Activating Token Index: 569