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

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

Neuron 1263 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1120. Min Act: -0.0001

Data Index: 429324 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1109. Min Act: -0.0001

Data Index: 744843 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1305669 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.1014. Min Act: -0.0001

Data Index: 516590 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0974. Min Act: -0.0001

Data Index: 202416 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1012172 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0981. Min Act: -0.0001

Data Index: 527600 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0984. Min Act: -0.0001

Data Index: 558254 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0942. Min Act: -0.0001

Data Index: 629326 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0968. Min Act: -0.0001

Data Index: 368970 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0969. Min Act: -0.0001

Data Index: 11000 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0959. Min Act: -0.0001

Data Index: 536251 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1026737 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0954. Min Act: -0.0001

Data Index: 930679 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0951. Min Act: -0.0001

Data Index: 44756 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0982. Min Act: -0.0001

Data Index: 46692 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0937. Min Act: -0.0001

Data Index: 662078 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0907. Min Act: -0.0001

Data Index: 626164 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0964. Min Act: -0.0001

Data Index: 880899 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.1120. Min Range: -0.1120

Max Act: 0.0986. Min Act: -0.0001

Data Index: 791094 (C4 (Web Text))

Max Activating Token Index: 769