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

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

Neuron 3924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1475607 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1510138 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7919. Min Act: -0.0000

Data Index: 330923 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.8018. Min Act: -0.0001

Data Index: 1616492 (Python Code)

Max Activating Token Index: 300

Text #4

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1607901 (Python Code)

Max Activating Token Index: 548

Text #5

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7486. Min Act: -0.0001

Data Index: 1380730 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1448716 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1501499 (Python Code)

Max Activating Token Index: 708

Text #8

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6276. Min Act: -0.0001

Data Index: 1604716 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6217. Min Act: -0.0000

Data Index: 36814 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6907. Min Act: -0.0001

Data Index: 1579151 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6412. Min Act: -0.0000

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1242628 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6124. Min Act: -0.0001

Data Index: 542421 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1650628 (Python Code)

Max Activating Token Index: 574

Text #15

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6010. Min Act: -0.0001

Data Index: 180398 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1533471 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1492985 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1629729 (Python Code)

Max Activating Token Index: 245

Text #19

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6387. Min Act: -0.0000

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 555