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

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

Neuron 348 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0001

Data Index: 160618 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2769. Min Act: -0.0001

Data Index: 687311 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2550. Min Act: -0.0001

Data Index: 498043 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2482. Min Act: -0.0001

Data Index: 811728 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1102890 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1098139 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2253. Min Act: -0.0001

Data Index: 65395 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1060069 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2310. Min Act: -0.0001

Data Index: 820745 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1015089 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2400. Min Act: -0.0001

Data Index: 83131 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2269. Min Act: -0.0001

Data Index: 661613 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1209240 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2098. Min Act: -0.0001

Data Index: 54802 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2302. Min Act: -0.0001

Data Index: 91984 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1142544 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1352469 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2254. Min Act: -0.0001

Data Index: 1330607 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2105. Min Act: -0.0001

Data Index: 694745 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1288144 (C4 (Web Text))

Max Activating Token Index: 428