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

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

Neuron 5458 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: 2.8711. Min Range: -2.8711

Max Act: 2.8711. Min Act: -0.0002

Data Index: 303390 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.6863. Min Act: -0.0002

Data Index: 257577 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.7030. Min Act: -0.0002

Data Index: 544904 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.6680. Min Act: -0.0002

Data Index: 634570 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5746. Min Act: -0.0002

Data Index: 160655 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5425. Min Act: -0.0002

Data Index: 258254 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5401. Min Act: -0.0002

Data Index: 969445 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5892. Min Act: -0.0002

Data Index: 751925 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5703. Min Act: -0.0002

Data Index: 1171100 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5078. Min Act: -0.0002

Data Index: 711349 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5563. Min Act: -0.0002

Data Index: 1065097 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.5134. Min Act: -0.0002

Data Index: 921904 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.4591. Min Act: -0.0002

Data Index: 171321 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.4451. Min Act: -0.0002

Data Index: 184713 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.4690. Min Act: -0.0002

Data Index: 736510 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.4705. Min Act: -0.0002

Data Index: 71450 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.4589. Min Act: -0.0002

Data Index: 222693 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.3749. Min Act: -0.0002

Data Index: 294115 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.3949. Min Act: -0.0002

Data Index: 500680 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 2.8711. Min Range: -2.8711

Max Act: 2.3240. Min Act: -0.0002

Data Index: 870427 (C4 (Web Text))

Max Activating Token Index: 248