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

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

Neuron 3424 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.4014. Min Act: -0.0000

Data Index: 137834 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3031. Min Act: -0.0000

Data Index: 367994 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3231. Min Act: -0.0000

Data Index: 798702 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3161. Min Act: -0.0000

Data Index: 617652 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3273. Min Act: -0.0000

Data Index: 340764 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2973. Min Act: -0.0000

Data Index: 255828 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1081542 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1183865 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3115. Min Act: -0.0000

Data Index: 35866 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3108. Min Act: -0.0000

Data Index: 238104 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3125. Min Act: -0.0000

Data Index: 314530 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1328533 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3084. Min Act: -0.0000

Data Index: 691672 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2942. Min Act: -0.0000

Data Index: 367183 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2988. Min Act: -0.0000

Data Index: 665008 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2891. Min Act: -0.0000

Data Index: 370071 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2920. Min Act: -0.0000

Data Index: 335928 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1220313 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3081. Min Act: -0.0000

Data Index: 8654 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2677. Min Act: -0.0000

Data Index: 793159 (C4 (Web Text))

Max Activating Token Index: 983