Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 630 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0003

Data Index: 54909 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0851. Min Act: -0.0003

Data Index: 48721 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0807. Min Act: -0.0003

Data Index: 25381 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0800. Min Act: -0.0003

Data Index: 763886 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0752. Min Act: -0.0003

Data Index: 93271 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0697. Min Act: -0.0003

Data Index: 382525 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1052086 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1330416 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1261861 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0668. Min Act: -0.0003

Data Index: 702393 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1131631 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0665. Min Act: -0.0003

Data Index: 558656 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0648. Min Act: -0.0002

Data Index: 673527 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0627. Min Act: -0.0003

Data Index: 746341 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0658. Min Act: -0.0003

Data Index: 197301 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0641. Min Act: -0.0003

Data Index: 371346 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1248486 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0629. Min Act: -0.0003

Data Index: 306406 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0617. Min Act: -0.0002

Data Index: 768445 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0626. Min Act: -0.0003

Data Index: 206913 (C4 (Web Text))

Max Activating Token Index: 157