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

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

Neuron 3304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.8458. Min Act: -0.0000

Data Index: 978586 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.8042. Min Act: -0.0000

Data Index: 999524 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1059075 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.7607. Min Act: -0.0000

Data Index: 988250 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.5146. Min Act: -0.0000

Data Index: 963142 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.4911. Min Act: -0.0000

Data Index: 805245 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.5754. Min Act: -0.0000

Data Index: 542242 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3555. Min Act: -0.0000

Data Index: 422011 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3662. Min Act: -0.0000

Data Index: 273919 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3624. Min Act: -0.0000

Data Index: 606362 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1098033 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3599. Min Act: -0.0000

Data Index: 689836 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3048. Min Act: -0.0000

Data Index: 785369 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1584380 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3163. Min Act: -0.0000

Data Index: 481092 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.2178. Min Act: -0.0000

Data Index: 949612 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.2515. Min Act: -0.0000

Data Index: 330415 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1033003 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.3800. Min Act: -0.0000

Data Index: 330962 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.8458. Min Range: -1.8458

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1254361 (C4 (Web Text))

Max Activating Token Index: 37