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

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

Neuron 2667 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: 0.7134. Min Range: -0.7134

Max Act: 0.7134. Min Act: -0.0001

Data Index: 586408 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6619. Min Act: -0.0001

Data Index: 760783 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6607. Min Act: -0.0000

Data Index: 817520 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.5743. Min Act: -0.0001

Data Index: 961708 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6139. Min Act: -0.0001

Data Index: 727171 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.5353. Min Act: -0.0001

Data Index: 569430 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.6236. Min Act: -0.0000

Data Index: 513877 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.5458. Min Act: -0.0001

Data Index: 1051563 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.5512. Min Act: -0.0001

Data Index: 575622 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.5133. Min Act: -0.0001

Data Index: 195138 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.5183. Min Act: -0.0001

Data Index: 424628 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.4858. Min Act: -0.0001

Data Index: 1046106 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.4951. Min Act: -0.0001

Data Index: 378678 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.4196. Min Act: -0.0001

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.3599. Min Act: -0.0001

Data Index: 529076 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.4011. Min Act: -0.0001

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.4015. Min Act: -0.0000

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.3113. Min Act: -0.0001

Data Index: 11232 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.7134. Min Range: -0.7134

Max Act: 0.3140. Min Act: -0.0001

Data Index: 1117147 (C4 (Web Text))

Max Activating Token Index: 285