Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1182 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.6452. Min Act: -0.0001

Data Index: 418900 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.6945. Min Act: -0.0001

Data Index: 495573 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.4127. Min Act: -0.0001

Data Index: 846851 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.5293. Min Act: -0.0001

Data Index: 34092 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.7694. Min Act: -0.0001

Data Index: 799564 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 1.9168. Min Range: -1.9168

Max Act: 0.9938. Min Act: -0.0001

Data Index: 1265387 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.7553. Min Act: -0.0001

Data Index: 357964 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.4837. Min Act: -0.0001

Data Index: 826706 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.4436. Min Act: -0.0001

Data Index: 526810 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.2684. Min Act: -0.0001

Data Index: 73399 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.9168. Min Act: -0.0001

Data Index: 73063 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.1978. Min Act: -0.0001

Data Index: 981273 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.7782. Min Act: -0.0001

Data Index: 531277 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.2878. Min Act: -0.0001

Data Index: 411739 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.5786. Min Act: -0.0001

Data Index: 983277 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.6489. Min Act: -0.0001

Data Index: 1103088 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.5332. Min Act: -0.0001

Data Index: 1093551 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.4429. Min Act: -0.0001

Data Index: 187604 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.6077. Min Act: -0.0001

Data Index: 895255 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 1.9168. Min Range: -1.9168

Max Act: 1.6372. Min Act: -0.0001

Data Index: 881705 (C4 (Web Text))

Max Activating Token Index: 154