Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 58 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0003

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0150. Min Act: -0.0002

Data Index: 668224 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1180755 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1206580 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0119. Min Act: -0.0003

Data Index: 710202 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0118. Min Act: -0.0002

Data Index: 695510 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1518674 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1171479 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1342606 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0111. Min Act: -0.0003

Data Index: 781092 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0110. Min Act: -0.0003

Data Index: 621516 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0109. Min Act: -0.0003

Data Index: 7167 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0111. Min Act: -0.0003

Data Index: 77395 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0109. Min Act: -0.0003

Data Index: 992098 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0108. Min Act: -0.0003

Data Index: 883674 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1236768 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0107. Min Act: -0.0003

Data Index: 827530 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0103. Min Act: -0.0003

Data Index: 599006 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0105. Min Act: -0.0003

Data Index: 809050 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0105. Min Act: -0.0003

Data Index: 861416 (C4 (Web Text))

Max Activating Token Index: 636