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

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

Neuron 4322 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1037448 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.7227. Min Act: -0.0000

Data Index: 311385 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.6282. Min Act: -0.0000

Data Index: 999482 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5775. Min Act: -0.0000

Data Index: 237253 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5886. Min Act: -0.0000

Data Index: 341711 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.6431. Min Act: -0.0000

Data Index: 540128 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5790. Min Act: -0.0000

Data Index: 775092 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1358937 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5532. Min Act: -0.0000

Data Index: 369809 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5311. Min Act: -0.0000

Data Index: 951617 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5603. Min Act: -0.0000

Data Index: 604055 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1041254 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5389. Min Act: -0.0000

Data Index: 648541 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1258003 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1102293 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5485. Min Act: -0.0000

Data Index: 712347 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1341701 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5095. Min Act: -0.0000

Data Index: 832014 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5053. Min Act: -0.0000

Data Index: 589066 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.8070. Min Range: -0.8070

Max Act: 0.5526. Min Act: -0.0000

Data Index: 586618 (C4 (Web Text))

Max Activating Token Index: 79