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

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

Neuron 13 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: 1.7815. Min Range: -1.7815

Max Act: 1.7815. Min Act: -0.0002

Data Index: 139818 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.7427. Min Act: -0.0002

Data Index: 895647 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.5469. Min Act: -0.0002

Data Index: 991920 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.5339. Min Act: -0.0002

Data Index: 451538 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.4934. Min Act: -0.0002

Data Index: 1071468 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.5396. Min Act: -0.0002

Data Index: 349641 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.4441. Min Act: -0.0002

Data Index: 847098 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.4148. Min Act: -0.0002

Data Index: 1344756 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.4075. Min Act: -0.0002

Data Index: 505445 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.4334. Min Act: -0.0002

Data Index: 1306694 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3901. Min Act: -0.0002

Data Index: 628380 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.4084. Min Act: -0.0002

Data Index: 64577 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3677. Min Act: -0.0002

Data Index: 201369 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3671. Min Act: -0.0002

Data Index: 952303 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3994. Min Act: -0.0002

Data Index: 986442 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3622. Min Act: -0.0002

Data Index: 622827 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3529. Min Act: -0.0002

Data Index: 1256564 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3384. Min Act: -0.0002

Data Index: 781331 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3486. Min Act: -0.0002

Data Index: 257374 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.7815. Min Range: -1.7815

Max Act: 1.3737. Min Act: -0.0002

Data Index: 938720 (C4 (Web Text))

Max Activating Token Index: 511