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

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

Neuron 3211 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0652. Min Range: -1.0652

Max Act: 1.0652. Min Act: -0.0000

Data Index: 970249 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.0652. Min Range: -1.0652

Max Act: 1.0019. Min Act: -0.0000

Data Index: 811049 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8571. Min Act: -0.0001

Data Index: 774216 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.9299. Min Act: -0.0001

Data Index: 810666 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1207628 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8879. Min Act: -0.0000

Data Index: 769552 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1270678 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8092. Min Act: -0.0001

Data Index: 24883 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1203943 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7766. Min Act: -0.0001

Data Index: 755940 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7776. Min Act: -0.0001

Data Index: 152287 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7928. Min Act: -0.0001

Data Index: 613502 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7911. Min Act: -0.0001

Data Index: 102657 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7422. Min Act: -0.0001

Data Index: 503220 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7178. Min Act: -0.0001

Data Index: 1132342 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.6977. Min Act: -0.0001

Data Index: 979459 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7792. Min Act: -0.0000

Data Index: 162675 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7080. Min Act: -0.0001

Data Index: 744169 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7571. Min Act: -0.0001

Data Index: 500365 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 1.0652. Min Range: -1.0652

Max Act: 0.7835. Min Act: -0.0000

Data Index: 152733 (C4 (Web Text))

Max Activating Token Index: 606