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

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

Neuron 3056 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: 3.4147. Min Range: -3.4147

Max Act: 3.4147. Min Act: -0.0000

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.2587. Min Act: -0.0000

Data Index: 507651 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.8615. Min Act: -0.0000

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.9281. Min Act: -0.0001

Data Index: 823650 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 3.4147. Min Range: -3.4147

Max Act: 3.0125. Min Act: -0.0000

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.7313. Min Act: -0.0000

Data Index: 562966 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.9830. Min Act: -0.0000

Data Index: 9723 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.7992. Min Act: -0.0000

Data Index: 647043 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.9059. Min Act: -0.0000

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.7626. Min Act: -0.0000

Data Index: 19826 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.8450. Min Act: -0.0000

Data Index: 877947 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.8696. Min Act: -0.0000

Data Index: 901201 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.5893. Min Act: -0.0000

Data Index: 103257 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.6615. Min Act: -0.0000

Data Index: 695258 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.5861. Min Act: -0.0000

Data Index: 1285504 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.7396. Min Act: -0.0000

Data Index: 727506 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.5937. Min Act: -0.0000

Data Index: 692571 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.3763. Min Act: -0.0000

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.5803. Min Act: -0.0000

Data Index: 1249278 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.4147. Min Range: -3.4147

Max Act: 2.4321. Min Act: -0.0000

Data Index: 773540 (C4 (Web Text))

Max Activating Token Index: 85