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

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

Neuron 2515 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: 5.5362. Min Range: -5.5362

Max Act: 5.5362. Min Act: -0.0000

Data Index: 874561 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 5.5362. Min Range: -5.5362

Max Act: 5.0398. Min Act: -0.0000

Data Index: 974737 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.9923. Min Act: -0.0000

Data Index: 76867 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 5.5362. Min Range: -5.5362

Max Act: 5.0684. Min Act: -0.0000

Data Index: 83523 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.6622. Min Act: -0.0000

Data Index: 1054750 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.7476. Min Act: -0.0000

Data Index: 797843 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.5078. Min Act: -0.0000

Data Index: 70262 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.6968. Min Act: -0.0000

Data Index: 923458 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.5951. Min Act: -0.0000

Data Index: 355063 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.3859. Min Act: -0.0000

Data Index: 821686 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.7365. Min Act: -0.0000

Data Index: 724611 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.5473. Min Act: -0.0000

Data Index: 1156607 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.4264. Min Act: -0.0000

Data Index: 557515 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.3924. Min Act: -0.0000

Data Index: 998593 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.3948. Min Act: -0.0000

Data Index: 1142066 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.2287. Min Act: -0.0000

Data Index: 1254390 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.3822. Min Act: -0.0000

Data Index: 1011641 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.1592. Min Act: -0.0000

Data Index: 1162033 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.5028. Min Act: -0.0000

Data Index: 802127 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 5.5362. Min Range: -5.5362

Max Act: 4.5134. Min Act: -0.0000

Data Index: 819079 (C4 (Web Text))

Max Activating Token Index: 1012