Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1090 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.9223. Min Act: -0.0004

Data Index: 838418 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7367. Min Act: -0.0004

Data Index: 296603 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7080. Min Act: -0.0004

Data Index: 230597 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8237. Min Act: -0.0004

Data Index: 752820 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7287. Min Act: -0.0004

Data Index: 1351122 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7368. Min Act: -0.0004

Data Index: 1263405 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7633. Min Act: -0.0004

Data Index: 571595 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7000. Min Act: -0.0004

Data Index: 1071806 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6463. Min Act: -0.0004

Data Index: 1157066 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6677. Min Act: -0.0004

Data Index: 117003 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5426. Min Act: -0.0004

Data Index: 362498 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6740. Min Act: -0.0004

Data Index: 1288638 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6997. Min Act: -0.0004

Data Index: 239664 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6945. Min Act: -0.0004

Data Index: 1016152 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6267. Min Act: -0.0004

Data Index: 949019 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6009. Min Act: -0.0004

Data Index: 119056 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6589. Min Act: -0.0004

Data Index: 168174 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6810. Min Act: -0.0004

Data Index: 1151037 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7027. Min Act: -0.0004

Data Index: 490954 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6085. Min Act: -0.0004

Data Index: 623848 (C4 (Web Text))

Max Activating Token Index: 24