Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 915 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.7194. Min Act: -0.1700

Data Index: 285554 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.5785. Min Act: -0.1700

Data Index: 145755 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.4375. Min Act: -0.1700

Data Index: 121701 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.4218. Min Act: -0.1700

Data Index: 1102260 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.4218. Min Act: -0.1700

Data Index: 540308 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.4061. Min Act: -0.1700

Data Index: 949834 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.3591. Min Act: -0.1700

Data Index: 273703 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.3747. Min Act: -0.1700

Data Index: 456874 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.3120. Min Act: -0.1700

Data Index: 848584 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.3120. Min Act: -0.1700

Data Index: 770827 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2963. Min Act: -0.1700

Data Index: 199780 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.3120. Min Act: -0.1700

Data Index: 104270 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.3120. Min Act: -0.1700

Data Index: 187796 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2805. Min Act: -0.1700

Data Index: 41969 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1458738 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2805. Min Act: -0.1700

Data Index: 99417 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2648. Min Act: -0.1700

Data Index: 935543 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1147386 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2648. Min Act: -0.1700

Data Index: 532805 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 3.7194. Min Range: -3.7194

Max Act: 3.2648. Min Act: -0.1700

Data Index: 1002672 (C4 (Web Text))

Max Activating Token Index: 810