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

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

Neuron 5407 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: 3.6817. Min Range: -3.6817

Max Act: 3.6817. Min Act: -0.0001

Data Index: 789265 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.2599. Min Act: -0.0001

Data Index: 237117 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.1161. Min Act: -0.0001

Data Index: 853543 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.6817. Min Range: -3.6817

Max Act: 3.2065. Min Act: -0.0001

Data Index: 545167 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.9172. Min Act: -0.0001

Data Index: 408661 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.7170. Min Act: -0.0001

Data Index: 757178 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.8409. Min Act: -0.0001

Data Index: 489565 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.6506. Min Act: -0.0001

Data Index: 975688 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.6295. Min Act: -0.0001

Data Index: 1283791 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.9449. Min Act: -0.0001

Data Index: 259175 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.6765. Min Act: -0.0001

Data Index: 1253569 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.7985. Min Act: -0.0001

Data Index: 1102748 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5458. Min Act: -0.0001

Data Index: 694499 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5365. Min Act: -0.0001

Data Index: 417640 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5852. Min Act: -0.0001

Data Index: 526764 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.4573. Min Act: -0.0001

Data Index: 317315 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.0720. Min Act: -0.0001

Data Index: 1019686 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5869. Min Act: -0.0001

Data Index: 1333197 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.4777. Min Act: -0.0001

Data Index: 635178 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 3.6817. Min Range: -3.6817

Max Act: 2.5673. Min Act: -0.0001

Data Index: 656619 (C4 (Web Text))

Max Activating Token Index: 140