Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.3668. Min Act: -0.0001

Data Index: 84834 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.4175. Min Act: -0.0001

Data Index: 371237 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.3247. Min Act: -0.0001

Data Index: 764843 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.2456. Min Act: -0.0001

Data Index: 1131528 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.2491. Min Act: -0.0001

Data Index: 235037 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.1496. Min Act: -0.0001

Data Index: 944031 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.1530. Min Act: -0.0001

Data Index: 8487 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0920. Min Act: -0.0001

Data Index: 1329731 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.1566. Min Act: -0.0000

Data Index: 893045 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0803. Min Act: -0.0001

Data Index: 873660 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.1496. Min Act: -0.0001

Data Index: 1263766 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0346. Min Act: -0.0001

Data Index: 737054 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.1625. Min Act: -0.0001

Data Index: 519960 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0520. Min Act: -0.0001

Data Index: 909387 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0181. Min Act: -0.0001

Data Index: 351006 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0599. Min Act: -0.0001

Data Index: 20672 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0052. Min Act: -0.0001

Data Index: 1127007 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.4175. Min Range: -1.4175

Max Act: 0.9404. Min Act: -0.0001

Data Index: 771378 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0043. Min Act: -0.0001

Data Index: 115050 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.4175. Min Range: -1.4175

Max Act: 1.0060. Min Act: -0.0001

Data Index: 1186497 (C4 (Web Text))

Max Activating Token Index: 173