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

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

Neuron 2455 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.5662. Min Act: -0.0000

Data Index: 648915 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4456. Min Act: -0.0000

Data Index: 322433 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4673. Min Act: -0.0000

Data Index: 832212 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.5255. Min Act: 0.0000

Data Index: 958157 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1014201 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4813. Min Act: -0.0000

Data Index: 1304025 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4847. Min Act: -0.0000

Data Index: 332085 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4845. Min Act: -0.0000

Data Index: 999130 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1007351 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4561. Min Act: -0.0000

Data Index: 402884 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4889. Min Act: -0.0000

Data Index: 120242 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.5100. Min Act: -0.0000

Data Index: 690601 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4655. Min Act: -0.0000

Data Index: 773356 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4189. Min Act: -0.0000

Data Index: 514910 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4605. Min Act: -0.0000

Data Index: 533017 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4767. Min Act: -0.0000

Data Index: 349670 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4247. Min Act: -0.0000

Data Index: 386561 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.3854. Min Act: -0.0000

Data Index: 222768 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1215660 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.5662. Min Range: -0.5662

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1230551 (C4 (Web Text))

Max Activating Token Index: 49