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

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

Neuron 1544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0836. Min Act: -0.0001

Data Index: 252307 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9389. Min Act: -0.0001

Data Index: 148220 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8455. Min Act: -0.0001

Data Index: 370997 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7896. Min Act: -0.0001

Data Index: 69679 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7253. Min Act: -0.0001

Data Index: 491058 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7340. Min Act: -0.0001

Data Index: 99230 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7620. Min Act: -0.0001

Data Index: 933635 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6984. Min Act: -0.0001

Data Index: 1459045 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7169. Min Act: -0.0001

Data Index: 31969 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7375. Min Act: -0.0001

Data Index: 1620145 (Python Code)

Max Activating Token Index: 963

Text #10

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6930. Min Act: -0.0001

Data Index: 1143408 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6808. Min Act: -0.0001

Data Index: 1159426 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7047. Min Act: -0.0001

Data Index: 1370866 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7027. Min Act: -0.0001

Data Index: 158480 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7218. Min Act: -0.0001

Data Index: 1468874 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1441333 (Python Code)

Max Activating Token Index: 917

Text #16

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1498913 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6697. Min Act: -0.0001

Data Index: 965620 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6883. Min Act: -0.0001

Data Index: 295497 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6901. Min Act: -0.0001

Data Index: 418188 (C4 (Web Text))

Max Activating Token Index: 391