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

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

Neuron 1080 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0006

Data Index: 999295 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0799. Min Act: -0.0006

Data Index: 1153529 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0766. Min Act: -0.0006

Data Index: 912530 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0721. Min Act: -0.0006

Data Index: 1228846 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0759. Min Act: -0.0006

Data Index: 86333 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0722. Min Act: -0.0006

Data Index: 49455 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0721. Min Act: -0.0006

Data Index: 369370 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0702. Min Act: -0.0006

Data Index: 520443 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0674. Min Act: -0.0006

Data Index: 969850 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0677. Min Act: -0.0006

Data Index: 229190 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0704. Min Act: -0.0006

Data Index: 128351 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0674. Min Act: -0.0006

Data Index: 1275039 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0701. Min Act: -0.0006

Data Index: 768447 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0638. Min Act: -0.0006

Data Index: 807971 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0666. Min Act: -0.0006

Data Index: 921837 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0639. Min Act: -0.0006

Data Index: 178415 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0690. Min Act: -0.0006

Data Index: 788128 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0683. Min Act: -0.0006

Data Index: 867475 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0707. Min Act: -0.0006

Data Index: 1064952 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0650. Min Act: -0.0006

Data Index: 987849 (C4 (Web Text))

Max Activating Token Index: 588