Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 176 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8552. Min Act: -0.0003

Data Index: 1093623 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8791. Min Act: -0.0003

Data Index: 31243 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8162. Min Act: -0.0003

Data Index: 124605 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8397. Min Act: -0.0003

Data Index: 247529 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8381. Min Act: -0.0003

Data Index: 1099164 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8313. Min Act: -0.0003

Data Index: 856569 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8321. Min Act: -0.0003

Data Index: 792424 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7947. Min Act: -0.0003

Data Index: 819620 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8125. Min Act: -0.0003

Data Index: 135059 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8066. Min Act: -0.0003

Data Index: 933470 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7982. Min Act: -0.0003

Data Index: 393032 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7964. Min Act: -0.0003

Data Index: 521260 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7970. Min Act: -0.0003

Data Index: 1176669 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8171. Min Act: -0.0003

Data Index: 3758 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7628. Min Act: -0.0003

Data Index: 90455 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7620. Min Act: -0.0003

Data Index: 1253949 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.8076. Min Act: -0.0002

Data Index: 855026 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7745. Min Act: -0.0003

Data Index: 512248 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7545. Min Act: -0.0002

Data Index: 614778 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.8791. Min Range: -0.8791

Max Act: 0.7756. Min Act: -0.0003

Data Index: 1352727 (C4 (Web Text))

Max Activating Token Index: 547