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

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

Neuron 996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.3473. Min Act: -0.0000

Data Index: 1353270 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.3379. Min Act: -0.0000

Data Index: 325179 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.3415. Min Act: -0.0000

Data Index: 796961 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.1335. Min Act: -0.0000

Data Index: 1073786 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.4523. Min Act: -0.0000

Data Index: 1240387 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 2.4523. Min Range: -2.4523

Max Act: 2.1682. Min Act: -0.0000

Data Index: 391421 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8752. Min Act: -0.0000

Data Index: 539981 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.9556. Min Act: -0.0000

Data Index: 508055 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8413. Min Act: -0.0000

Data Index: 244862 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.9125. Min Act: -0.0000

Data Index: 1084094 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8763. Min Act: -0.0000

Data Index: 631380 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7631. Min Act: -0.0000

Data Index: 173340 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8655. Min Act: -0.0000

Data Index: 474983 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1228796 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.8501. Min Act: -0.0000

Data Index: 934075 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7301. Min Act: -0.0000

Data Index: 892824 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.6933. Min Act: -0.0000

Data Index: 969374 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.7966. Min Act: -0.0000

Data Index: 838172 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.6989. Min Act: -0.0000

Data Index: 20310 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 2.4523. Min Range: -2.4523

Max Act: 1.6837. Min Act: -0.0000

Data Index: 141502 (C4 (Web Text))

Max Activating Token Index: 79