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

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

Neuron 4240 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.7116. Min Act: 0.0001

Data Index: 478802 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6757. Min Act: -0.0000

Data Index: 850258 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6623. Min Act: 0.0001

Data Index: 1305991 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6550. Min Act: -0.0000

Data Index: 17385 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5917. Min Act: -0.0000

Data Index: 798826 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5737. Min Act: -0.0000

Data Index: 466372 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5503. Min Act: 0.0000

Data Index: 616704 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5348. Min Act: -0.0000

Data Index: 462178 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1215518 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5621. Min Act: -0.0000

Data Index: 734099 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1156628 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5336. Min Act: -0.0000

Data Index: 641931 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5474. Min Act: -0.0000

Data Index: 773412 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5114. Min Act: -0.0000

Data Index: 164703 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5241. Min Act: -0.0000

Data Index: 163957 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5390. Min Act: 0.0001

Data Index: 264094 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4668. Min Act: 0.0001

Data Index: 683103 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5255. Min Act: -0.0000

Data Index: 56214 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4982. Min Act: -0.0000

Data Index: 751365 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4897. Min Act: -0.0000

Data Index: 713207 (C4 (Web Text))

Max Activating Token Index: 101