Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1252 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9342. Min Act: -0.0001

Data Index: 519852 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9835. Min Act: -0.0002

Data Index: 1131716 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6759. Min Act: -0.0002

Data Index: 1269297 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6563. Min Act: -0.0002

Data Index: 1062621 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6501. Min Act: -0.0002

Data Index: 269855 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5070. Min Act: -0.0001

Data Index: 1043196 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5788. Min Act: -0.0001

Data Index: 206452 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4915. Min Act: -0.0001

Data Index: 417587 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6313. Min Act: -0.0002

Data Index: 181700 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6261. Min Act: -0.0002

Data Index: 975501 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6431. Min Act: -0.0001

Data Index: 403732 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5570. Min Act: -0.0001

Data Index: 156875 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6411. Min Act: -0.0002

Data Index: 719722 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4991. Min Act: -0.0001

Data Index: 922185 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4282. Min Act: -0.0002

Data Index: 607945 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3255. Min Act: -0.0001

Data Index: 1305985 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4497. Min Act: -0.0002

Data Index: 1129562 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4207. Min Act: -0.0002

Data Index: 763107 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4213. Min Act: -0.0001

Data Index: 308659 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.2975. Min Act: -0.0002

Data Index: 1066162 (C4 (Web Text))

Max Activating Token Index: 1023