Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 644 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9749. Min Act: -0.0001

Data Index: 1268898 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.9014. Min Act: -0.0001

Data Index: 972756 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6867. Min Act: -0.0001

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6074. Min Act: -0.0001

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.6844. Min Act: -0.0001

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4324. Min Act: -0.0001

Data Index: 977929 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4688. Min Act: -0.0001

Data Index: 1261188 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3543. Min Act: -0.0001

Data Index: 457074 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3541. Min Act: -0.0001

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.4243. Min Act: -0.0001

Data Index: 1142129 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3054. Min Act: -0.0001

Data Index: 1292566 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3095. Min Act: -0.0001

Data Index: 323452 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3157. Min Act: -0.0001

Data Index: 608617 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3092. Min Act: -0.0001

Data Index: 1319961 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.2939. Min Act: -0.0001

Data Index: 947521 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3328. Min Act: -0.0001

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3466. Min Act: -0.0001

Data Index: 1302025 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.1796. Min Act: -0.0001

Data Index: 87282 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.3247. Min Act: -0.0001

Data Index: 448806 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.9749. Min Range: -1.9749

Max Act: 1.2471. Min Act: -0.0001

Data Index: 495226 (C4 (Web Text))

Max Activating Token Index: 927