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

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

Neuron 4452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.4287. Min Act: -0.0002

Data Index: 1048105 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.2450. Min Act: -0.0002

Data Index: 123482 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.1968. Min Act: -0.0002

Data Index: 1179822 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.2381. Min Act: -0.0002

Data Index: 557586 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.2130. Min Act: -0.0002

Data Index: 544461 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.0437. Min Act: -0.0002

Data Index: 97256 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.1501. Min Act: -0.0002

Data Index: 1107087 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.0353. Min Act: -0.0002

Data Index: 953561 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.9956. Min Act: -0.0002

Data Index: 840885 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.1600. Min Act: -0.0002

Data Index: 565492 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.0173. Min Act: -0.0002

Data Index: 244521 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.0264. Min Act: -0.0002

Data Index: 683384 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.9472. Min Act: -0.0002

Data Index: 381113 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.0311. Min Act: -0.0002

Data Index: 281996 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.9411. Min Act: -0.0002

Data Index: 333634 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.9400. Min Act: -0.0002

Data Index: 1167028 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.4287. Min Range: -1.4287

Max Act: 1.0323. Min Act: -0.0002

Data Index: 1326081 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.9361. Min Act: -0.0002

Data Index: 749364 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.8976. Min Act: -0.0002

Data Index: 749371 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.4287. Min Range: -1.4287

Max Act: 0.9273. Min Act: -0.0002

Data Index: 120452 (C4 (Web Text))

Max Activating Token Index: 971