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

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

Neuron 1070 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.0278. Min Range: -3.0278

Max Act: 3.0278. Min Act: -0.1700

Data Index: 403172 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.9543. Min Act: -0.1700

Data Index: 569154 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.9544. Min Act: -0.1700

Data Index: 807221 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8956. Min Act: -0.1700

Data Index: 488160 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8894. Min Act: -0.1700

Data Index: 1301592 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8754. Min Act: -0.1700

Data Index: 807948 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8711. Min Act: -0.1700

Data Index: 782488 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8490. Min Act: -0.1700

Data Index: 682369 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8712. Min Act: -0.1700

Data Index: 694683 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8415. Min Act: -0.1700

Data Index: 225029 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8507. Min Act: -0.1700

Data Index: 60615 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8691. Min Act: -0.1700

Data Index: 1169003 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8807. Min Act: -0.1700

Data Index: 674981 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8572. Min Act: -0.1700

Data Index: 476966 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8583. Min Act: -0.1700

Data Index: 1329774 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8460. Min Act: -0.1700

Data Index: 480568 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8354. Min Act: -0.1700

Data Index: 1557317 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8226. Min Act: -0.1700

Data Index: 854804 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8421. Min Act: -0.1700

Data Index: 1250513 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.0278. Min Range: -3.0278

Max Act: 2.8376. Min Act: -0.1700

Data Index: 749348 (C4 (Web Text))

Max Activating Token Index: 509