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

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

Neuron 66 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2674. Min Act: -0.0000

Data Index: 429988 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2747. Min Act: -0.0000

Data Index: 11134 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2629. Min Act: -0.0000

Data Index: 513317 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2392. Min Act: -0.0000

Data Index: 589139 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2583. Min Act: -0.0000

Data Index: 41754 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2453. Min Act: -0.0000

Data Index: 619988 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2486. Min Act: -0.0000

Data Index: 975152 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2292. Min Act: -0.0000

Data Index: 661774 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2057. Min Act: -0.0000

Data Index: 71060 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2228. Min Act: -0.0000

Data Index: 49294 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2102. Min Act: -0.0000

Data Index: 814334 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1148966 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1348797 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2536. Min Act: -0.0000

Data Index: 795521 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2210. Min Act: -0.0000

Data Index: 707555 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2162. Min Act: -0.0000

Data Index: 532578 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2254. Min Act: -0.0000

Data Index: 453718 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2156. Min Act: -0.0000

Data Index: 207698 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2196. Min Act: -0.0000

Data Index: 99465 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.2747. Min Range: -0.2747

Max Act: 0.2294. Min Act: -0.0000

Data Index: 589510 (C4 (Web Text))

Max Activating Token Index: 770