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

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

Neuron 771 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0260. Min Range: -1.0260

Max Act: 1.0260. Min Act: -0.0001

Data Index: 986539 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8998. Min Act: -0.0001

Data Index: 487320 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8500. Min Act: -0.0001

Data Index: 525879 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8359. Min Act: -0.0001

Data Index: 1323604 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8802. Min Act: -0.0001

Data Index: 858190 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8779. Min Act: -0.0001

Data Index: 1117315 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.7489. Min Act: -0.0001

Data Index: 419090 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8523. Min Act: -0.0001

Data Index: 1188583 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8711. Min Act: -0.0001

Data Index: 658687 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8435. Min Act: -0.0001

Data Index: 288754 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.7947. Min Act: -0.0001

Data Index: 785221 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8023. Min Act: -0.0001

Data Index: 72772 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8000. Min Act: -0.0001

Data Index: 413389 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1243350 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.7750. Min Act: -0.0001

Data Index: 200950 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8562. Min Act: -0.0001

Data Index: 64748 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.7964. Min Act: -0.0001

Data Index: 553453 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8350. Min Act: -0.0001

Data Index: 293109 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.7867. Min Act: -0.0001

Data Index: 89642 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.0260. Min Range: -1.0260

Max Act: 0.8119. Min Act: -0.0001

Data Index: 729034 (C4 (Web Text))

Max Activating Token Index: 53