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

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

Neuron 393 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: 2.9315. Min Range: -2.9315

Max Act: 2.9315. Min Act: -0.1700

Data Index: 543933 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.7563. Min Act: -0.1700

Data Index: 1576112 (Python Code)

Max Activating Token Index: 656

Text #2

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6784. Min Act: -0.1700

Data Index: 1646406 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6535. Min Act: -0.1700

Data Index: 1539396 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6258. Min Act: -0.1699

Data Index: 1332952 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6092. Min Act: -0.1700

Data Index: 1525670 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6224. Min Act: -0.1700

Data Index: 716888 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6143. Min Act: -0.1700

Data Index: 31941 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.6130. Min Act: -0.1700

Data Index: 1576173 (Python Code)

Max Activating Token Index: 560

Text #9

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5825. Min Act: -0.1700

Data Index: 1437902 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5946. Min Act: -0.1700

Data Index: 374628 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5757. Min Act: -0.1700

Data Index: 449088 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5730. Min Act: -0.1700

Data Index: 1417444 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5398. Min Act: -0.1700

Data Index: 1381710 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5597. Min Act: -0.1700

Data Index: 1587320 (Python Code)

Max Activating Token Index: 766

Text #15

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5591. Min Act: -0.1700

Data Index: 1564915 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5607. Min Act: -0.1700

Data Index: 1640064 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5523. Min Act: -0.1700

Data Index: 1464526 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5276. Min Act: -0.1699

Data Index: 175448 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 2.9315. Min Range: -2.9315

Max Act: 2.5427. Min Act: -0.1700

Data Index: 1621147 (Python Code)

Max Activating Token Index: 144