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

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

Neuron 3664 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4033. Min Act: -0.0001

Data Index: 96105 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4158. Min Act: -0.0001

Data Index: 565192 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1348475 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3522. Min Act: -0.0001

Data Index: 462723 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3407. Min Act: -0.0001

Data Index: 540812 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3334. Min Act: -0.0001

Data Index: 47304 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3530. Min Act: -0.0001

Data Index: 836095 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3458. Min Act: -0.0001

Data Index: 458454 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2934. Min Act: -0.0001

Data Index: 781010 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3078. Min Act: -0.0001

Data Index: 1227553 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1017753 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3377. Min Act: -0.0001

Data Index: 846543 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3287. Min Act: -0.0001

Data Index: 560872 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2943. Min Act: -0.0001

Data Index: 729107 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1028287 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3184. Min Act: -0.0001

Data Index: 991437 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2841. Min Act: -0.0001

Data Index: 403113 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.3019. Min Act: -0.0001

Data Index: 341566 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2913. Min Act: -0.0001

Data Index: 808729 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.4596. Min Range: -0.4596

Max Act: 0.2880. Min Act: -0.0001

Data Index: 30588 (C4 (Web Text))

Max Activating Token Index: 824