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

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

Neuron 734 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: 3.8937. Min Range: -3.8937

Max Act: 3.8937. Min Act: -0.0000

Data Index: 1072057 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.9197. Min Act: 0.0001

Data Index: 144804 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.6118. Min Act: -0.0000

Data Index: 546964 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.8109. Min Act: -0.0000

Data Index: 1444142 (Python Code)

Max Activating Token Index: 619

Text #4

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.7472. Min Act: -0.0000

Data Index: 967053 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.7362. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.6737. Min Act: -0.0000

Data Index: 833555 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.5998. Min Act: -0.0000

Data Index: 74147 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.7242. Min Act: -0.0000

Data Index: 946539 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.4161. Min Act: 0.0000

Data Index: 268016 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.5092. Min Act: 0.0000

Data Index: 948905 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.6519. Min Act: -0.0000

Data Index: 427162 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.6373. Min Act: -0.0000

Data Index: 988167 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.6373. Min Act: 0.0001

Data Index: 854272 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.4611. Min Act: 0.0001

Data Index: 946696 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.4468. Min Act: -0.0000

Data Index: 890134 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.3818. Min Act: -0.0000

Data Index: 299167 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.3488. Min Act: -0.0000

Data Index: 231093 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.4732. Min Act: -0.0000

Data Index: 519388 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 3.8937. Min Range: -3.8937

Max Act: 2.3234. Min Act: -0.0000

Data Index: 890859 (C4 (Web Text))

Max Activating Token Index: 706