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

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

Neuron 1754 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1098151 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5974. Min Act: -0.0000

Data Index: 655570 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1228459 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5451. Min Act: -0.0000

Data Index: 577281 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5418. Min Act: -0.0000

Data Index: 307530 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5418. Min Act: -0.0000

Data Index: 85241 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5364. Min Act: -0.0000

Data Index: 932305 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5060. Min Act: -0.0000

Data Index: 754794 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5007. Min Act: -0.0000

Data Index: 420803 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1148169 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4988. Min Act: -0.0000

Data Index: 36996 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.5057. Min Act: -0.0000

Data Index: 744670 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4752. Min Act: -0.0000

Data Index: 455924 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4692. Min Act: -0.0000

Data Index: 531563 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4659. Min Act: -0.0000

Data Index: 223029 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4501. Min Act: -0.0000

Data Index: 534375 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4656. Min Act: -0.0000

Data Index: 82916 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1284618 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4326. Min Act: -0.0000

Data Index: 324878 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.6413. Min Range: -0.6413

Max Act: 0.4505. Min Act: -0.0000

Data Index: 210656 (C4 (Web Text))

Max Activating Token Index: 727