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

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

Neuron 2793 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0001

Data Index: 785956 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1036. Min Act: -0.0001

Data Index: 908696 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1274101 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1013. Min Act: -0.0001

Data Index: 128135 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1261698 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1574911 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1032614 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1478927 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0918. Min Act: -0.0001

Data Index: 498408 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0953. Min Act: -0.0001

Data Index: 431157 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1349610 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1041544 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0913. Min Act: -0.0001

Data Index: 93008 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1266008 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0939. Min Act: -0.0001

Data Index: 261402 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0918. Min Act: -0.0001

Data Index: 967636 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0934. Min Act: -0.0001

Data Index: 39978 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0936. Min Act: -0.0001

Data Index: 277496 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0930. Min Act: -0.0001

Data Index: 816953 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0920. Min Act: -0.0001

Data Index: 653064 (C4 (Web Text))

Max Activating Token Index: 643