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

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

Neuron 2085 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5628. Min Act: -0.0001

Data Index: 132742 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3801. Min Act: -0.0001

Data Index: 1310246 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4974. Min Act: -0.0001

Data Index: 97921 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3910. Min Act: -0.0001

Data Index: 1042091 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4345. Min Act: -0.0001

Data Index: 869280 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3104. Min Act: -0.0001

Data Index: 523039 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3472. Min Act: -0.0001

Data Index: 541759 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4142. Min Act: -0.0001

Data Index: 940396 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.1675. Min Act: -0.0001

Data Index: 1123463 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3619. Min Act: -0.0001

Data Index: 640080 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3234. Min Act: -0.0001

Data Index: 611439 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3586. Min Act: -0.0001

Data Index: 1062176 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3330. Min Act: -0.0001

Data Index: 607199 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3243. Min Act: -0.0001

Data Index: 36329 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3502. Min Act: -0.0001

Data Index: 417521 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.2996. Min Act: -0.0001

Data Index: 120146 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.2222. Min Act: -0.0001

Data Index: 893246 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.2935. Min Act: -0.0001

Data Index: 664608 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.2892. Min Act: -0.0001

Data Index: 1100806 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.2889. Min Act: -0.0001

Data Index: 978304 (C4 (Web Text))

Max Activating Token Index: 403