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

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

Neuron 3712 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: 0.6372. Min Range: -0.6372

Max Act: 0.6372. Min Act: -0.0002

Data Index: 474060 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6091. Min Act: -0.0002

Data Index: 335649 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.6079. Min Act: -0.0002

Data Index: 888443 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5919. Min Act: -0.0002

Data Index: 592190 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5808. Min Act: -0.0002

Data Index: 593127 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5809. Min Act: -0.0003

Data Index: 818354 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5700. Min Act: -0.0002

Data Index: 447594 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5791. Min Act: -0.0002

Data Index: 456104 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5517. Min Act: -0.0002

Data Index: 480342 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5469. Min Act: -0.0002

Data Index: 776973 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5570. Min Act: -0.0003

Data Index: 1057743 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5457. Min Act: -0.0002

Data Index: 950627 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5457. Min Act: -0.0002

Data Index: 557383 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5604. Min Act: -0.0003

Data Index: 1134202 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5591. Min Act: -0.0002

Data Index: 887104 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5455. Min Act: -0.0003

Data Index: 841381 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5460. Min Act: -0.0002

Data Index: 623225 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5522. Min Act: -0.0002

Data Index: 316560 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5458. Min Act: -0.0002

Data Index: 602685 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.6372. Min Range: -0.6372

Max Act: 0.5394. Min Act: -0.0002

Data Index: 696002 (C4 (Web Text))

Max Activating Token Index: 129