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

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

Neuron 5 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4309. Min Act: -0.0003

Data Index: 31067 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3292. Min Act: -0.0003

Data Index: 427672 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3990. Min Act: -0.0003

Data Index: 479548 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3926. Min Act: -0.0003

Data Index: 699304 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4020. Min Act: -0.0003

Data Index: 698173 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4129. Min Act: -0.0003

Data Index: 1233490 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4066. Min Act: -0.0003

Data Index: 1112751 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3940. Min Act: -0.0003

Data Index: 849151 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3777. Min Act: -0.0003

Data Index: 1226278 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3740. Min Act: -0.0003

Data Index: 1345500 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4027. Min Act: -0.0003

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3961. Min Act: -0.0003

Data Index: 919335 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3434. Min Act: -0.0003

Data Index: 1099692 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3574. Min Act: -0.0003

Data Index: 352826 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3738. Min Act: -0.0003

Data Index: 979650 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3620. Min Act: -0.0003

Data Index: 606478 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3776. Min Act: -0.0003

Data Index: 203958 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3653. Min Act: -0.0003

Data Index: 224309 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3919. Min Act: -0.0003

Data Index: 166916 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4024. Min Act: -0.0003

Data Index: 915651 (C4 (Web Text))

Max Activating Token Index: 202