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

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

Neuron 2095 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: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0001

Data Index: 208149 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1262472 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1166. Min Act: -0.0001

Data Index: 711631 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1136. Min Act: -0.0001

Data Index: 36966 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1054. Min Act: -0.0000

Data Index: 515625 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1016. Min Act: -0.0001

Data Index: 325898 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1020. Min Act: -0.0001

Data Index: 781857 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1205689 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1025. Min Act: -0.0001

Data Index: 707901 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1033. Min Act: -0.0001

Data Index: 230052 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0994. Min Act: -0.0001

Data Index: 436642 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0951. Min Act: -0.0001

Data Index: 390225 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0974. Min Act: -0.0000

Data Index: 242552 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0899. Min Act: 0.0000

Data Index: 647895 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0913. Min Act: -0.0001

Data Index: 821975 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1133031 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0993. Min Act: -0.0001

Data Index: 179912 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0942. Min Act: -0.0001

Data Index: 822437 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1039602 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0917. Min Act: -0.0001

Data Index: 434929 (C4 (Web Text))

Max Activating Token Index: 445