Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 946 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3350. Min Act: -0.0003

Data Index: 1454893 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3421. Min Act: -0.0003

Data Index: 1466560 (Python Code)

Max Activating Token Index: 413

Text #2

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3203. Min Act: -0.0003

Data Index: 1523518 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3203. Min Act: -0.0003

Data Index: 1650761 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3457. Min Act: -0.0003

Data Index: 1553902 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3090. Min Act: -0.0003

Data Index: 1487378 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3024. Min Act: -0.0003

Data Index: 1420100 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3205. Min Act: -0.0003

Data Index: 1643064 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3184. Min Act: -0.0003

Data Index: 1487531 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3183. Min Act: -0.0003

Data Index: 1647786 (Python Code)

Max Activating Token Index: 224

Text #10

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3288. Min Act: -0.0003

Data Index: 1444915 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3088. Min Act: -0.0003

Data Index: 1365226 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3183. Min Act: -0.0003

Data Index: 1431397 (Python Code)

Max Activating Token Index: 572

Text #13

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3177. Min Act: -0.0003

Data Index: 1515947 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3268. Min Act: -0.0003

Data Index: 1593454 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3058. Min Act: -0.0003

Data Index: 1461122 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3037. Min Act: -0.0003

Data Index: 1553570 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3070. Min Act: -0.0003

Data Index: 1403806 (Python Code)

Max Activating Token Index: 369

Text #18

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.3124. Min Act: -0.0003

Data Index: 1513081 (Python Code)

Max Activating Token Index: 160

Text #19

Max Range: 0.3457. Min Range: -0.3457

Max Act: 0.2883. Min Act: -0.0003

Data Index: 1627586 (Python Code)

Max Activating Token Index: 577