Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5737 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2223. Min Act: -0.0002

Data Index: 838931 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2196. Min Act: -0.0002

Data Index: 33939 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2131. Min Act: -0.0002

Data Index: 270871 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2121. Min Act: -0.0002

Data Index: 692902 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2121. Min Act: -0.0002

Data Index: 327384 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2111. Min Act: -0.0002

Data Index: 36640 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2091. Min Act: -0.0002

Data Index: 1199976 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2103. Min Act: -0.0002

Data Index: 157223 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.2022. Min Act: -0.0002

Data Index: 493954 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1970. Min Act: -0.0003

Data Index: 961127 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1947. Min Act: -0.0002

Data Index: 958842 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1969. Min Act: -0.0002

Data Index: 437671 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1951. Min Act: -0.0002

Data Index: 21096 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1899. Min Act: -0.0002

Data Index: 264155 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1922. Min Act: -0.0002

Data Index: 128800 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1898. Min Act: -0.0002

Data Index: 1309241 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1881. Min Act: -0.0002

Data Index: 161977 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1939. Min Act: -0.0002

Data Index: 1279536 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1927. Min Act: -0.0002

Data Index: 573695 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.2223. Min Range: -0.2223

Max Act: 0.1860. Min Act: -0.0002

Data Index: 1324927 (C4 (Web Text))

Max Activating Token Index: 172