Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1037 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1187. Min Act: -0.0001

Data Index: 318517 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1229. Min Act: -0.0001

Data Index: 291686 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1212. Min Act: -0.0001

Data Index: 291669 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1087. Min Act: -0.0001

Data Index: 986950 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1037. Min Act: -0.0001

Data Index: 936588 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1055. Min Act: -0.0001

Data Index: 320361 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1022. Min Act: -0.0001

Data Index: 270088 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1038. Min Act: -0.0001

Data Index: 904398 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1030. Min Act: -0.0001

Data Index: 205654 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1041. Min Act: -0.0001

Data Index: 589822 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1023. Min Act: -0.0001

Data Index: 92440 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1017. Min Act: -0.0001

Data Index: 803987 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1020. Min Act: -0.0001

Data Index: 962068 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1005. Min Act: -0.0001

Data Index: 173858 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1016. Min Act: -0.0001

Data Index: 852259 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1049961 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0995. Min Act: -0.0001

Data Index: 638828 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1015. Min Act: -0.0001

Data Index: 328263 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1165848 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0932. Min Act: -0.0001

Data Index: 290406 (C4 (Web Text))

Max Activating Token Index: 1010