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

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

Neuron 1679 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: 0.7419. Min Range: -0.7419

Max Act: 0.7419. Min Act: -0.0001

Data Index: 598441 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.7299. Min Act: -0.0001

Data Index: 229715 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6697. Min Act: -0.0001

Data Index: 804214 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6449. Min Act: -0.0001

Data Index: 956763 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6422. Min Act: -0.0001

Data Index: 1103661 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6440. Min Act: -0.0001

Data Index: 8363 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5909. Min Act: -0.0001

Data Index: 21820 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6557. Min Act: -0.0001

Data Index: 1311665 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5903. Min Act: -0.0001

Data Index: 802454 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6070. Min Act: -0.0001

Data Index: 61834 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.7276. Min Act: -0.0001

Data Index: 965740 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1354541 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6016. Min Act: -0.0001

Data Index: 644061 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5167. Min Act: -0.0001

Data Index: 197424 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6040. Min Act: -0.0001

Data Index: 982753 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5858. Min Act: -0.0001

Data Index: 816787 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5618. Min Act: -0.0001

Data Index: 256146 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5263. Min Act: -0.0001

Data Index: 766180 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1317631 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5444. Min Act: -0.0001

Data Index: 121561 (C4 (Web Text))

Max Activating Token Index: 256