Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2890 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.8202. Min Act: -0.0001

Data Index: 191103 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1040953 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.7144. Min Act: -0.0000

Data Index: 192103 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.7492. Min Act: -0.0000

Data Index: 65222 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.7265. Min Act: -0.0001

Data Index: 667336 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1065096 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6874. Min Act: -0.0000

Data Index: 431176 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6747. Min Act: -0.0000

Data Index: 870061 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6749. Min Act: -0.0001

Data Index: 129747 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6510. Min Act: -0.0001

Data Index: 665787 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1215456 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6469. Min Act: -0.0000

Data Index: 29554 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6190. Min Act: -0.0000

Data Index: 966678 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6345. Min Act: -0.0000

Data Index: 399638 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6360. Min Act: -0.0001

Data Index: 714073 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6302. Min Act: -0.0000

Data Index: 880149 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6064. Min Act: -0.0000

Data Index: 484703 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1217236 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6109. Min Act: -0.0000

Data Index: 775110 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.8202. Min Range: -0.8202

Max Act: 0.6255. Min Act: -0.0000

Data Index: 813300 (C4 (Web Text))

Max Activating Token Index: 964