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

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

Neuron 177 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2897. Min Range: -2.2897

Max Act: 2.1171. Min Act: -0.0000

Data Index: 753980 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1545281 (Python Code)

Max Activating Token Index: 948

Text #2

Max Range: 2.2897. Min Range: -2.2897

Max Act: 2.2897. Min Act: -0.0000

Data Index: 461602 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.9180. Min Act: -0.0000

Data Index: 393670 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8721. Min Act: -0.0000

Data Index: 772869 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1629638 (Python Code)

Max Activating Token Index: 729

Text #6

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8561. Min Act: -0.0000

Data Index: 408902 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8280. Min Act: -0.0000

Data Index: 638972 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 2.2897. Min Range: -2.2897

Max Act: 2.0430. Min Act: -0.0000

Data Index: 801815 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.9467. Min Act: -0.0000

Data Index: 605509 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1162314 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8180. Min Act: -0.0000

Data Index: 1409905 (Python Code)

Max Activating Token Index: 987

Text #12

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.9050. Min Act: -0.0000

Data Index: 482144 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8104. Min Act: -0.0000

Data Index: 558979 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8947. Min Act: -0.0000

Data Index: 879112 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.2897. Min Range: -2.2897

Max Act: 2.0034. Min Act: -0.0000

Data Index: 1649408 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.7870. Min Act: -0.0000

Data Index: 399320 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8982. Min Act: -0.0000

Data Index: 1132304 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.8908. Min Act: -0.0000

Data Index: 402516 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 2.2897. Min Range: -2.2897

Max Act: 1.9243. Min Act: -0.0000

Data Index: 1547109 (Python Code)

Max Activating Token Index: 973