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

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

Neuron 4250 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: 1.8775. Min Range: -1.8775

Max Act: 1.8775. Min Act: -0.0000

Data Index: 749658 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.5043. Min Act: -0.0000

Data Index: 550852 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.4755. Min Act: -0.0000

Data Index: 244932 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3692. Min Act: -0.0000

Data Index: 397475 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.4330. Min Act: -0.0000

Data Index: 286354 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.5021. Min Act: -0.0000

Data Index: 141702 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3565. Min Act: -0.0000

Data Index: 959673 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1022847 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3138. Min Act: -0.0000

Data Index: 264455 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3821. Min Act: -0.0000

Data Index: 152743 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3059. Min Act: -0.0000

Data Index: 470209 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2150. Min Act: -0.0000

Data Index: 119304 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2749. Min Act: -0.0000

Data Index: 598804 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2775. Min Act: -0.0000

Data Index: 910082 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.3247. Min Act: -0.0000

Data Index: 28944 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2694. Min Act: -0.0000

Data Index: 522842 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2403. Min Act: -0.0000

Data Index: 68965 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1281057 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.2711. Min Act: -0.0000

Data Index: 283164 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.8775. Min Range: -1.8775

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1019968 (C4 (Web Text))

Max Activating Token Index: 782