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

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

Neuron 3316 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.4183. Min Act: -0.0001

Data Index: 160188 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.2858. Min Act: -0.0001

Data Index: 659075 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1227131 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1009730 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1518. Min Act: -0.0001

Data Index: 19021 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1340260 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1766. Min Act: -0.0001

Data Index: 729198 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1316. Min Act: -0.0001

Data Index: 742053 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1175. Min Act: -0.0001

Data Index: 1085025 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1533742 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0590. Min Act: -0.0001

Data Index: 675773 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0960. Min Act: -0.0001

Data Index: 1207822 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.1685. Min Act: -0.0000

Data Index: 1207636 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.4183. Min Range: -1.4183

Max Act: 0.9652. Min Act: -0.0001

Data Index: 1413446 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0575. Min Act: -0.0001

Data Index: 1170029 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0430. Min Act: -0.0001

Data Index: 491736 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0464. Min Act: -0.0001

Data Index: 1233783 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0925. Min Act: -0.0001

Data Index: 606828 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0343. Min Act: -0.0001

Data Index: 698795 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.4183. Min Range: -1.4183

Max Act: 1.0275. Min Act: -0.0000

Data Index: 89009 (C4 (Web Text))

Max Activating Token Index: 146