Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.4115. Min Act: -0.0000

Data Index: 397428 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1270836 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3602. Min Act: -0.0000

Data Index: 742411 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3701. Min Act: -0.0000

Data Index: 479316 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1333694 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1250355 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1260667 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3449. Min Act: -0.0000

Data Index: 108932 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1062391 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3301. Min Act: -0.0000

Data Index: 230588 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1138591 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3087. Min Act: -0.0000

Data Index: 608804 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1584356 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3423. Min Act: -0.0000

Data Index: 120753 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1330144 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1021274 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3131. Min Act: -0.0000

Data Index: 671522 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1318170 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3160. Min Act: -0.0000

Data Index: 534957 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3164. Min Act: -0.0000

Data Index: 719836 (C4 (Web Text))

Max Activating Token Index: 104