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

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

Neuron 810 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: 0.6027. Min Range: -0.6027

Max Act: 0.6027. Min Act: -0.0002

Data Index: 1150088 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5864. Min Act: -0.0002

Data Index: 745346 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5593. Min Act: -0.0002

Data Index: 456153 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5706. Min Act: -0.0002

Data Index: 95788 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5606. Min Act: -0.0002

Data Index: 363263 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5516. Min Act: -0.0002

Data Index: 477655 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5415. Min Act: -0.0002

Data Index: 1224900 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5488. Min Act: -0.0002

Data Index: 121397 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5516. Min Act: -0.0002

Data Index: 585285 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5436. Min Act: -0.0002

Data Index: 1333810 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5489. Min Act: -0.0002

Data Index: 41802 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5544. Min Act: -0.0002

Data Index: 198634 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5346. Min Act: -0.0002

Data Index: 71266 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5473. Min Act: -0.0002

Data Index: 1277671 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5352. Min Act: -0.0002

Data Index: 121092 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5420. Min Act: -0.0002

Data Index: 547597 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5405. Min Act: -0.0002

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5310. Min Act: -0.0002

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5314. Min Act: -0.0002

Data Index: 984293 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.6027. Min Range: -0.6027

Max Act: 0.5285. Min Act: -0.0002

Data Index: 995707 (C4 (Web Text))

Max Activating Token Index: 384