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

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

Neuron 144 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: 3.6804. Min Range: -3.6804

Max Act: 3.6804. Min Act: -0.1700

Data Index: 36666 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6705. Min Act: -0.1700

Data Index: 90674 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6636. Min Act: -0.1700

Data Index: 981544 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6567. Min Act: -0.1700

Data Index: 137964 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6416. Min Act: -0.1700

Data Index: 766200 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6349. Min Act: -0.1700

Data Index: 328820 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6053. Min Act: -0.1700

Data Index: 666059 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.6094. Min Act: -0.1700

Data Index: 669405 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5864. Min Act: -0.1700

Data Index: 683689 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5901. Min Act: -0.1700

Data Index: 346213 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5637. Min Act: -0.1700

Data Index: 1058567 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5639. Min Act: -0.1700

Data Index: 751730 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5480. Min Act: -0.1700

Data Index: 545925 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5182. Min Act: -0.1700

Data Index: 670499 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5295. Min Act: -0.1700

Data Index: 844681 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5269. Min Act: -0.1700

Data Index: 755081 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5205. Min Act: -0.1700

Data Index: 841133 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5317. Min Act: -0.1700

Data Index: 916215 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5313. Min Act: -0.1700

Data Index: 444692 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 3.6804. Min Range: -3.6804

Max Act: 3.5034. Min Act: -0.1700

Data Index: 394705 (C4 (Web Text))

Max Activating Token Index: 346