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

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

Neuron 2877 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8459. Min Act: -0.0004

Data Index: 43430 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8701. Min Act: -0.0004

Data Index: 93575 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8373. Min Act: -0.0004

Data Index: 1339562 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8903. Min Act: -0.0004

Data Index: 191847 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7533. Min Act: -0.0004

Data Index: 458019 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8742. Min Act: -0.0004

Data Index: 526115 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8079. Min Act: -0.0004

Data Index: 1241178 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7784. Min Act: -0.0004

Data Index: 739029 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8041. Min Act: -0.0004

Data Index: 578218 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7490. Min Act: -0.0004

Data Index: 1062507 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7398. Min Act: -0.0004

Data Index: 112250 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7001. Min Act: -0.0004

Data Index: 435683 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8045. Min Act: -0.0004

Data Index: 228623 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7840. Min Act: -0.0004

Data Index: 1303114 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7397. Min Act: -0.0004

Data Index: 441053 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.6809. Min Act: -0.0004

Data Index: 713207 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.8019. Min Act: -0.0004

Data Index: 1057463 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7805. Min Act: -0.0004

Data Index: 336474 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.9034. Min Act: -0.0004

Data Index: 444789 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.9034. Min Range: -0.9034

Max Act: 0.7038. Min Act: -0.0004

Data Index: 1324646 (C4 (Web Text))

Max Activating Token Index: 43