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

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

Neuron 4587 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.4996. Min Act: -0.0000

Data Index: 764960 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9787. Min Act: -0.0000

Data Index: 333683 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 2.4996. Min Range: -2.4996

Max Act: 2.1254. Min Act: -0.0000

Data Index: 821885 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.9554. Min Act: -0.0000

Data Index: 571996 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7005. Min Act: -0.0000

Data Index: 868162 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.8603. Min Act: -0.0000

Data Index: 1015400 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7795. Min Act: -0.0000

Data Index: 86300 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.8286. Min Act: -0.0000

Data Index: 205095 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.8695. Min Act: -0.0000

Data Index: 1257342 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.7838. Min Act: -0.0000

Data Index: 676027 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.6301. Min Act: -0.0000

Data Index: 1570324 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1541432 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1365482 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.5751. Min Act: -0.0000

Data Index: 425589 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.6157. Min Act: -0.0000

Data Index: 8557 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.4123. Min Act: -0.0000

Data Index: 305816 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1537758 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.5267. Min Act: -0.0000

Data Index: 959642 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.5261. Min Act: -0.0000

Data Index: 954705 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 2.4996. Min Range: -2.4996

Max Act: 1.4856. Min Act: -0.0000

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 940