Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6110 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.3887. Min Act: -0.0000

Data Index: 217547 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.2957. Min Act: -0.0000

Data Index: 408812 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.2532. Min Act: -0.0000

Data Index: 9931 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.9773. Min Act: -0.0000

Data Index: 1182352 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.1767. Min Act: -0.0000

Data Index: 942547 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.0540. Min Act: -0.0000

Data Index: 1215789 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.0504. Min Act: -0.0000

Data Index: 1316298 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.0521. Min Act: -0.0000

Data Index: 530646 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.0122. Min Act: -0.0000

Data Index: 1029926 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.9978. Min Act: -0.0000

Data Index: 959094 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.8834. Min Act: -0.0000

Data Index: 991252 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.9787. Min Act: -0.0000

Data Index: 27191 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.9822. Min Act: -0.0000

Data Index: 809357 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.9189. Min Act: -0.0000

Data Index: 523126 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.9207. Min Act: -0.0000

Data Index: 17890 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 2.3887. Min Range: -2.3887

Max Act: 2.0117. Min Act: -0.0000

Data Index: 1179817 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.8054. Min Act: -0.0000

Data Index: 12463 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.8878. Min Act: -0.0000

Data Index: 761474 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.7574. Min Act: -0.0000

Data Index: 361770 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 2.3887. Min Range: -2.3887

Max Act: 1.7441. Min Act: -0.0000

Data Index: 739465 (C4 (Web Text))

Max Activating Token Index: 125