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

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

Neuron 1979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0001

Data Index: 247672 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5774. Min Act: -0.0001

Data Index: 486343 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5836. Min Act: -0.0001

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5586. Min Act: -0.0001

Data Index: 845848 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5059. Min Act: -0.0001

Data Index: 225716 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5402. Min Act: -0.0001

Data Index: 1009569 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5497. Min Act: -0.0001

Data Index: 1315622 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5375. Min Act: -0.0001

Data Index: 456640 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5102. Min Act: -0.0001

Data Index: 271186 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5088. Min Act: -0.0001

Data Index: 864195 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1000265 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5002. Min Act: -0.0001

Data Index: 1152789 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5205. Min Act: -0.0001

Data Index: 196664 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4819. Min Act: -0.0001

Data Index: 917448 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5120. Min Act: -0.0001

Data Index: 1193545 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5113. Min Act: -0.0000

Data Index: 315515 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5102. Min Act: -0.0001

Data Index: 269229 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1348326 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5061. Min Act: -0.0001

Data Index: 195291 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4729. Min Act: -0.0000

Data Index: 901042 (C4 (Web Text))

Max Activating Token Index: 165