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

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

Neuron 1336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4382. Min Act: -0.0001

Data Index: 727151 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1160811 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3720. Min Act: -0.0001

Data Index: 902865 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3147. Min Act: -0.0001

Data Index: 701494 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3208. Min Act: -0.0001

Data Index: 1002990 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1187003 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3023. Min Act: -0.0001

Data Index: 561068 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3041. Min Act: -0.0001

Data Index: 1138845 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3246. Min Act: -0.0001

Data Index: 1009080 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1003129 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3068. Min Act: -0.0001

Data Index: 125831 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3171. Min Act: -0.0001

Data Index: 1292409 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3011. Min Act: -0.0001

Data Index: 417695 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2895. Min Act: -0.0001

Data Index: 643117 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3119. Min Act: -0.0001

Data Index: 866412 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2997. Min Act: -0.0001

Data Index: 242947 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2992. Min Act: -0.0001

Data Index: 336447 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2878. Min Act: -0.0001

Data Index: 719761 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1349579 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2848. Min Act: -0.0001

Data Index: 339136 (C4 (Web Text))

Max Activating Token Index: 166