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

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

Neuron 3204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1314. Min Act: -0.0000

Data Index: 472117 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1184. Min Act: -0.0000

Data Index: 887771 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1143. Min Act: -0.0000

Data Index: 305069 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1083836 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1015. Min Act: -0.0000

Data Index: 166918 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1459508 (Python Code)

Max Activating Token Index: 679

Text #6

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0980. Min Act: -0.0000

Data Index: 814044 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0949. Min Act: -0.0000

Data Index: 111783 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0979. Min Act: -0.0000

Data Index: 538918 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1235990 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1290344 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1107792 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0934. Min Act: -0.0000

Data Index: 498537 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0935. Min Act: -0.0000

Data Index: 477410 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0929. Min Act: -0.0000

Data Index: 482356 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1268842 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1117612 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1273795 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0921. Min Act: -0.0000

Data Index: 429404 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.0916. Min Act: -0.0000

Data Index: 229000 (C4 (Web Text))

Max Activating Token Index: 673