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

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

Neuron 1011 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.7381. Min Act: -0.0001

Data Index: 217745 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.7544. Min Act: -0.0001

Data Index: 962458 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.2278. Min Act: -0.0001

Data Index: 301645 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.2670. Min Act: -0.0001

Data Index: 760240 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 3.7544. Min Range: -3.7544

Max Act: 2.7663. Min Act: -0.0001

Data Index: 613639 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.2574. Min Act: -0.0001

Data Index: 1309939 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0965. Min Act: -0.0001

Data Index: 533771 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0836. Min Act: -0.0001

Data Index: 1226816 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.1734. Min Act: -0.0001

Data Index: 966668 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.7544. Min Range: -3.7544

Max Act: 2.8527. Min Act: -0.0001

Data Index: 470065 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.7544. Min Range: -3.7544

Max Act: 2.9782. Min Act: -0.0001

Data Index: 906355 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0950. Min Act: -0.0001

Data Index: 234285 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.2252. Min Act: -0.0001

Data Index: 516635 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0811. Min Act: -0.0001

Data Index: 501088 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.2348. Min Act: -0.0001

Data Index: 204126 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0879. Min Act: -0.0001

Data Index: 1000206 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0837. Min Act: -0.0001

Data Index: 853544 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 3.7544. Min Range: -3.7544

Max Act: 2.9415. Min Act: -0.0001

Data Index: 1339074 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.1879. Min Act: -0.0001

Data Index: 1025487 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 3.7544. Min Range: -3.7544

Max Act: 3.0492. Min Act: -0.0001

Data Index: 538166 (C4 (Web Text))

Max Activating Token Index: 89