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

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

Neuron 2212 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: 0.7096. Min Range: -0.7096

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1168446 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5943. Min Act: -0.0000

Data Index: 22689 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5669. Min Act: -0.0000

Data Index: 7968 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5597. Min Act: -0.0000

Data Index: 188068 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1313309 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5754. Min Act: -0.0000

Data Index: 625884 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5951. Min Act: -0.0000

Data Index: 616382 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5651. Min Act: -0.0000

Data Index: 137569 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5516. Min Act: -0.0000

Data Index: 26037 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5542. Min Act: -0.0000

Data Index: 261278 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5262. Min Act: -0.0000

Data Index: 777411 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5110. Min Act: -0.0000

Data Index: 158249 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.4946. Min Act: -0.0000

Data Index: 742353 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1578296 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.4919. Min Act: -0.0000

Data Index: 87221 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1169556 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1312143 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1275286 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1256964 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.7096. Min Range: -0.7096

Max Act: 0.4987. Min Act: -0.0000

Data Index: 737401 (C4 (Web Text))

Max Activating Token Index: 80