Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1178 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1214852 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.1052. Min Act: -0.0001

Data Index: 694182 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9109. Min Act: -0.0001

Data Index: 991533 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9758. Min Act: -0.0001

Data Index: 670431 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9270. Min Act: -0.0001

Data Index: 206208 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9257. Min Act: -0.0001

Data Index: 1282405 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9403. Min Act: -0.0001

Data Index: 406265 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.8624. Min Act: -0.0001

Data Index: 89531 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1158690 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7739. Min Act: -0.0001

Data Index: 821104 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7846. Min Act: -0.0001

Data Index: 1289378 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1016485 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7521. Min Act: -0.0001

Data Index: 463600 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7477. Min Act: -0.0001

Data Index: 388555 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1124882 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7358. Min Act: -0.0001

Data Index: 187919 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7082. Min Act: -0.0001

Data Index: 771446 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1083723 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7253. Min Act: -0.0001

Data Index: 184391 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.6749. Min Act: -0.0001

Data Index: 1165193 (C4 (Web Text))

Max Activating Token Index: 726