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

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

Neuron 1542 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: 4.1889. Min Range: -4.1889

Max Act: 4.1889. Min Act: -0.1700

Data Index: 819173 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0019. Min Act: -0.1700

Data Index: 1472719 (Python Code)

Max Activating Token Index: 681

Text #2

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9594. Min Act: -0.1700

Data Index: 666129 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9421. Min Act: -0.1700

Data Index: 1594884 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9393. Min Act: -0.1700

Data Index: 86718 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9516. Min Act: -0.1700

Data Index: 745024 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8998. Min Act: -0.1700

Data Index: 37898 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8567. Min Act: -0.1700

Data Index: 807888 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8571. Min Act: -0.1699

Data Index: 1462005 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8452. Min Act: -0.1700

Data Index: 1386954 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8689. Min Act: -0.1700

Data Index: 1446063 (Python Code)

Max Activating Token Index: 495

Text #11

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8630. Min Act: -0.1696

Data Index: 1446444 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8441. Min Act: -0.1700

Data Index: 272788 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8425. Min Act: -0.1700

Data Index: 1502400 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8243. Min Act: -0.1700

Data Index: 1533864 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1260288 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8229. Min Act: -0.1699

Data Index: 1304882 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.7975. Min Act: -0.1700

Data Index: 1656613 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.7845. Min Act: -0.1699

Data Index: 1630085 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.7784. Min Act: -0.1700

Data Index: 1471327 (Python Code)

Max Activating Token Index: 451