Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1942 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1173152 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1308749 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8703. Min Act: -0.0000

Data Index: 935774 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1124931 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7995. Min Act: -0.0000

Data Index: 567394 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8150. Min Act: -0.0000

Data Index: 450904 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8143. Min Act: -0.0000

Data Index: 466909 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1402918 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1064860 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7915. Min Act: -0.0000

Data Index: 781800 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7850. Min Act: -0.0000

Data Index: 569587 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1279518 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7881. Min Act: -0.0000

Data Index: 940555 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1145651 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1462219 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1265161 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1432804 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1129932 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1179998 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7104. Min Act: -0.0000

Data Index: 161638 (C4 (Web Text))

Max Activating Token Index: 841