Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1615 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3530. Min Act: -0.0005

Data Index: 489865 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3508. Min Act: -0.0005

Data Index: 876403 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3232. Min Act: -0.0005

Data Index: 998560 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.3215. Min Act: -0.0004

Data Index: 90089 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2920. Min Act: -0.0005

Data Index: 688731 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2897. Min Act: -0.0005

Data Index: 768900 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2812. Min Act: -0.0005

Data Index: 507168 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2598. Min Act: -0.0005

Data Index: 97242 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2972. Min Act: -0.0005

Data Index: 1079742 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2702. Min Act: -0.0005

Data Index: 5152 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2694. Min Act: -0.0005

Data Index: 1198202 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2499. Min Act: -0.0005

Data Index: 556041 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2762. Min Act: -0.0005

Data Index: 477770 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2617. Min Act: -0.0005

Data Index: 837908 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2700. Min Act: -0.0005

Data Index: 216704 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2489. Min Act: -0.0005

Data Index: 742682 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2571. Min Act: -0.0004

Data Index: 359732 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2578. Min Act: -0.0005

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2673. Min Act: -0.0004

Data Index: 20577 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.3530. Min Range: -0.3530

Max Act: 0.2356. Min Act: -0.0005

Data Index: 877650 (C4 (Web Text))

Max Activating Token Index: 88