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

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

Neuron 3812 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.8865. Min Act: -0.0000

Data Index: 1593975 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1129195 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1549808 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5623. Min Act: -0.0000

Data Index: 1377735 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.7554. Min Act: -0.0000

Data Index: 433401 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.7630. Min Act: -0.0000

Data Index: 1396940 (Python Code)

Max Activating Token Index: 252

Text #6

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6291. Min Act: -0.0000

Data Index: 1056509 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6277. Min Act: -0.0000

Data Index: 1370886 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1310455 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4724. Min Act: -0.0000

Data Index: 581626 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4731. Min Act: -0.0000

Data Index: 830154 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1638750 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.6147. Min Act: -0.0000

Data Index: 1015179 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1674 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1387915 (Python Code)

Max Activating Token Index: 367

Text #15

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1389969 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1536459 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1486293 (Python Code)

Max Activating Token Index: 991

Text #18

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1507437 (Python Code)

Max Activating Token Index: 491

Text #19

Max Range: 1.9993. Min Range: -1.9993

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1495429 (Python Code)

Max Activating Token Index: 222