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

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

Neuron 4970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9160. Min Act: -0.0000

Data Index: 141621 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9472. Min Act: -0.0000

Data Index: 35889 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8776. Min Act: -0.0000

Data Index: 660208 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1111812 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8549. Min Act: -0.0000

Data Index: 820730 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8383. Min Act: -0.0000

Data Index: 285961 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8046. Min Act: -0.0000

Data Index: 402930 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8826. Min Act: -0.0000

Data Index: 318326 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8249. Min Act: -0.0000

Data Index: 834851 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1045731 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8641. Min Act: -0.0000

Data Index: 592412 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8025. Min Act: -0.0000

Data Index: 313368 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8041. Min Act: -0.0000

Data Index: 441803 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7700. Min Act: -0.0000

Data Index: 267358 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1129042 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8020. Min Act: -0.0000

Data Index: 414888 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7745. Min Act: -0.0000

Data Index: 17566 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7978. Min Act: -0.0000

Data Index: 797154 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8013. Min Act: -0.0000

Data Index: 538404 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7617. Min Act: -0.0000

Data Index: 623589 (C4 (Web Text))

Max Activating Token Index: 84