Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2981. Min Act: -0.0001

Data Index: 959047 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2729. Min Act: -0.0001

Data Index: 10841 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2601. Min Act: -0.0001

Data Index: 772315 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2743. Min Act: -0.0001

Data Index: 645842 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1353211 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1208480 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2293. Min Act: -0.0001

Data Index: 576085 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2344. Min Act: -0.0001

Data Index: 293020 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2231. Min Act: -0.0001

Data Index: 1204889 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.1964. Min Act: -0.0001

Data Index: 488443 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2205. Min Act: -0.0001

Data Index: 540848 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2111. Min Act: -0.0001

Data Index: 542317 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1122651 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2033. Min Act: -0.0001

Data Index: 864163 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1267986 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1077881 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2124. Min Act: -0.0001

Data Index: 7873 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1133760 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.1785. Min Act: -0.0001

Data Index: 221144 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.1849. Min Act: -0.0001

Data Index: 945965 (C4 (Web Text))

Max Activating Token Index: 124