Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1799 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2672. Min Act: -0.0006

Data Index: 46959 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2642. Min Act: -0.0006

Data Index: 185246 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2620. Min Act: -0.0006

Data Index: 567602 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2615. Min Act: -0.0006

Data Index: 809770 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2606. Min Act: -0.0006

Data Index: 1113179 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2647. Min Act: -0.0006

Data Index: 423714 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2592. Min Act: -0.0006

Data Index: 662601 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2589. Min Act: -0.0006

Data Index: 937240 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2598. Min Act: -0.0006

Data Index: 1228011 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2589. Min Act: -0.0006

Data Index: 1027735 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2582. Min Act: -0.0006

Data Index: 885245 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2584. Min Act: -0.0006

Data Index: 1012136 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2630. Min Act: -0.0006

Data Index: 654810 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2580. Min Act: -0.0006

Data Index: 496483 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2626. Min Act: -0.0006

Data Index: 650732 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2568. Min Act: -0.0006

Data Index: 488577 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2571. Min Act: -0.0006

Data Index: 774420 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2567. Min Act: -0.0006

Data Index: 1126723 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2566. Min Act: -0.0006

Data Index: 288624 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2569. Min Act: -0.0006

Data Index: 1113769 (C4 (Web Text))

Max Activating Token Index: 976