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

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

Neuron 3712 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0002

Data Index: 187480 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0429. Min Act: -0.0001

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9585. Min Act: -0.0002

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0204. Min Act: -0.0002

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0933. Min Act: -0.0001

Data Index: 525075 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8533. Min Act: -0.0001

Data Index: 42734 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9288. Min Act: -0.0002

Data Index: 1224087 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9428. Min Act: -0.0002

Data Index: 265928 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8838. Min Act: -0.0002

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8941. Min Act: -0.0001

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8477. Min Act: -0.0002

Data Index: 300802 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8775. Min Act: -0.0001

Data Index: 664862 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8153. Min Act: -0.0001

Data Index: 305990 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8525. Min Act: -0.0001

Data Index: 964823 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8738. Min Act: -0.0001

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7880. Min Act: -0.0002

Data Index: 1126708 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7823. Min Act: -0.0002

Data Index: 8812 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8051. Min Act: -0.0001

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8068. Min Act: -0.0001

Data Index: 627881 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8003. Min Act: -0.0001

Data Index: 255163 (C4 (Web Text))

Max Activating Token Index: 760