Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3853 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3728. Min Range: -2.3728

Max Act: 2.3728. Min Act: -0.0000

Data Index: 384365 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.8414. Min Act: -0.0000

Data Index: 109455 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.8347. Min Act: -0.0000

Data Index: 280818 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.8893. Min Act: -0.0000

Data Index: 533729 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6665. Min Act: -0.0000

Data Index: 306331 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.8507. Min Act: -0.0000

Data Index: 457087 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1199232 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6897. Min Act: -0.0000

Data Index: 832616 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6656. Min Act: -0.0000

Data Index: 1255712 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6668. Min Act: -0.0000

Data Index: 425305 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.7636. Min Act: -0.0000

Data Index: 37301 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6639. Min Act: -0.0000

Data Index: 95362 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.7566. Min Act: -0.0000

Data Index: 246626 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.7520. Min Act: -0.0000

Data Index: 448993 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6484. Min Act: -0.0000

Data Index: 984954 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1135535 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6219. Min Act: -0.0000

Data Index: 433700 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.7097. Min Act: -0.0000

Data Index: 235812 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.5951. Min Act: -0.0000

Data Index: 784609 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.3728. Min Range: -2.3728

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1007644 (C4 (Web Text))

Max Activating Token Index: 631