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

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

Neuron 409 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.9082. Min Act: -0.0000

Data Index: 645505 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.6627. Min Act: -0.0000

Data Index: 1097096 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5480. Min Act: -0.0000

Data Index: 1310410 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4936. Min Act: -0.0000

Data Index: 575599 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5021. Min Act: -0.0000

Data Index: 923027 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4902. Min Act: -0.0000

Data Index: 47801 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1106146 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4999. Min Act: -0.0000

Data Index: 748091 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1351398 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.5159. Min Act: -0.0000

Data Index: 552993 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4133. Min Act: -0.0000

Data Index: 203418 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.3971. Min Act: -0.0000

Data Index: 878070 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.3988. Min Act: -0.0000

Data Index: 55261 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.3820. Min Act: -0.0000

Data Index: 412208 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.3698. Min Act: -0.0000

Data Index: 229578 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.3819. Min Act: -0.0000

Data Index: 344944 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.2651. Min Act: -0.0000

Data Index: 383977 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.2515. Min Act: -0.0000

Data Index: 217392 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.4039. Min Act: -0.0000

Data Index: 202591 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.9082. Min Range: -1.9082

Max Act: 1.3946. Min Act: -0.0000

Data Index: 79451 (C4 (Web Text))

Max Activating Token Index: 837