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

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

Neuron 1178 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0003

Data Index: 241370 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0003

Data Index: 500225 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0003

Data Index: 39005 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0003

Data Index: 411144 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0002

Data Index: 435388 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0002

Data Index: 248482 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0003

Data Index: 135723 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0003

Data Index: 41345 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0002

Data Index: 655794 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0003

Data Index: 516462 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0003

Data Index: 755662 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0003

Data Index: 714715 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1169786 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1008884 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0003

Data Index: 299973 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1257899 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0002

Data Index: 993670 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1348243 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1194405 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0003

Data Index: 130687 (C4 (Web Text))

Max Activating Token Index: 412