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

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

Neuron 1497 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: 0.4303. Min Range: -0.4303

Max Act: 0.4303. Min Act: -0.0000

Data Index: 928932 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1068336 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1026346 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1271848 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3334. Min Act: -0.0000

Data Index: 646996 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3200. Min Act: -0.0000

Data Index: 368323 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3173. Min Act: -0.0000

Data Index: 805931 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3047. Min Act: -0.0000

Data Index: 337344 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2972. Min Act: -0.0000

Data Index: 516497 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3167. Min Act: -0.0000

Data Index: 562808 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2875. Min Act: -0.0000

Data Index: 860451 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1144066 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3026. Min Act: -0.0000

Data Index: 704103 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3013. Min Act: -0.0000

Data Index: 114122 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2989. Min Act: -0.0000

Data Index: 369837 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1214764 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2831. Min Act: -0.0000

Data Index: 893347 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2818. Min Act: -0.0000

Data Index: 826175 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2890. Min Act: -0.0000

Data Index: 211526 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1142179 (C4 (Web Text))

Max Activating Token Index: 489