Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3610. Min Act: -0.0001

Data Index: 542710 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3103. Min Act: -0.0001

Data Index: 149637 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3188. Min Act: -0.0001

Data Index: 1018264 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3085. Min Act: -0.0001

Data Index: 767524 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2907. Min Act: -0.0001

Data Index: 90787 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2999. Min Act: -0.0001

Data Index: 481130 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1099962 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2924. Min Act: -0.0001

Data Index: 511027 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1006768 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2849. Min Act: -0.0001

Data Index: 1291511 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2844. Min Act: -0.0000

Data Index: 581099 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2894. Min Act: 0.0001

Data Index: 959835 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1263344 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2820. Min Act: -0.0001

Data Index: 917103 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2638. Min Act: -0.0000

Data Index: 945948 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2775. Min Act: 0.0001

Data Index: 176743 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2659. Min Act: -0.0001

Data Index: 649288 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1133116 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2552. Min Act: -0.0001

Data Index: 715621 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2654. Min Act: -0.0001

Data Index: 627689 (C4 (Web Text))

Max Activating Token Index: 979