Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2843 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4782. Min Act: -0.0002

Data Index: 550637 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3996. Min Act: -0.0002

Data Index: 841956 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4119. Min Act: -0.0003

Data Index: 79072 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3718. Min Act: -0.0002

Data Index: 864331 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3599. Min Act: -0.0002

Data Index: 570338 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3345. Min Act: -0.0002

Data Index: 325906 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3404. Min Act: -0.0002

Data Index: 660081 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2766. Min Act: -0.0002

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2855. Min Act: -0.0002

Data Index: 101028 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2729. Min Act: -0.0003

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2641. Min Act: -0.0002

Data Index: 181039 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2490. Min Act: -0.0002

Data Index: 1097820 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2378. Min Act: -0.0002

Data Index: 1041679 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2519. Min Act: -0.0002

Data Index: 363860 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2577. Min Act: -0.0002

Data Index: 531156 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2217. Min Act: -0.0002

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2167. Min Act: -0.0003

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2269. Min Act: -0.0002

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2314. Min Act: -0.0002

Data Index: 747362 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2064. Min Act: -0.0002

Data Index: 503947 (C4 (Web Text))

Max Activating Token Index: 50