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

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

Neuron 935 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0001

Data Index: 877411 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0917. Min Act: -0.0001

Data Index: 837717 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0822. Min Act: -0.0001

Data Index: 17881 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0841. Min Act: -0.0001

Data Index: 791227 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0810. Min Act: -0.0001

Data Index: 980746 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0784. Min Act: -0.0001

Data Index: 789300 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0791. Min Act: -0.0001

Data Index: 816245 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0783. Min Act: -0.0001

Data Index: 296935 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0797. Min Act: -0.0001

Data Index: 736863 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0760. Min Act: -0.0001

Data Index: 159726 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0760. Min Act: -0.0001

Data Index: 333401 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1184739 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0791. Min Act: -0.0001

Data Index: 94973 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0723. Min Act: -0.0001

Data Index: 546357 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0712. Min Act: -0.0001

Data Index: 547463 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0775. Min Act: -0.0001

Data Index: 359222 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0739. Min Act: -0.0001

Data Index: 902632 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0723. Min Act: -0.0001

Data Index: 779612 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0722. Min Act: -0.0001

Data Index: 818892 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0699. Min Act: -0.0001

Data Index: 427213 (C4 (Web Text))

Max Activating Token Index: 21