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

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

Neuron 1380 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.3387. Min Act: -0.0001

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.8955. Min Act: -0.0002

Data Index: 715962 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.2970. Min Act: -0.0001

Data Index: 500606 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.4123. Min Act: -0.0001

Data Index: 1322471 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.1269. Min Act: -0.0001

Data Index: 1198219 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.3222. Min Act: -0.0001

Data Index: 1196548 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.7651. Min Act: -0.0002

Data Index: 54557 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.1233. Min Act: -0.0002

Data Index: 1089778 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.2269. Min Act: -0.0001

Data Index: 617897 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.0610. Min Act: -0.0002

Data Index: 45538 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.9313. Min Act: -0.0001

Data Index: 170173 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.9187. Min Act: -0.0001

Data Index: 619413 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.7453. Min Act: -0.0002

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.0362. Min Act: -0.0001

Data Index: 228245 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.4980. Min Act: -0.0001

Data Index: 451705 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.8747. Min Act: -0.0002

Data Index: 229204 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.1159. Min Act: -0.0001

Data Index: 194544 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.5413. Min Act: -0.0002

Data Index: 163281 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.5413. Min Range: -3.5413

Max Act: 2.9347. Min Act: -0.0002

Data Index: 1299064 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 3.5413. Min Range: -3.5413

Max Act: 3.0602. Min Act: -0.0002

Data Index: 505898 (C4 (Web Text))

Max Activating Token Index: 882