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

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

Neuron 3 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: 0.3341. Min Range: -0.3341

Max Act: 0.3341. Min Act: -0.0000

Data Index: 147998 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1186479 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2939. Min Act: -0.0000

Data Index: 467566 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3255. Min Act: -0.0000

Data Index: 90070 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1170782 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2906. Min Act: -0.0000

Data Index: 521849 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2845. Min Act: -0.0000

Data Index: 913429 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1061033 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2845. Min Act: -0.0000

Data Index: 88679 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2818. Min Act: -0.0000

Data Index: 154566 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2810. Min Act: -0.0000

Data Index: 955863 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2698. Min Act: -0.0000

Data Index: 18716 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2878. Min Act: -0.0000

Data Index: 351770 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2758. Min Act: -0.0000

Data Index: 317234 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2734. Min Act: -0.0000

Data Index: 419075 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2810. Min Act: -0.0000

Data Index: 335576 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1463713 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1008117 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1372416 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2607. Min Act: -0.0000

Data Index: 934142 (C4 (Web Text))

Max Activating Token Index: 925