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

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

Neuron 96 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: 6.4499. Min Range: -6.4499

Max Act: 6.4499. Min Act: -0.1700

Data Index: 732684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.1487. Min Act: -0.1700

Data Index: 85544 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.1427. Min Act: -0.1700

Data Index: 714327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.1458. Min Act: -0.1700

Data Index: 238085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.1290. Min Act: -0.1700

Data Index: 296749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.1026. Min Act: -0.1700

Data Index: 336635 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.1164. Min Act: -0.1700

Data Index: 965752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1106578 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0852. Min Act: -0.1700

Data Index: 459696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0941. Min Act: -0.1700

Data Index: 1018893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0719. Min Act: -0.1700

Data Index: 1197990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0820. Min Act: -0.1700

Data Index: 836761 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0317. Min Act: -0.1700

Data Index: 903107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0483. Min Act: -0.1700

Data Index: 532593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0618. Min Act: -0.1700

Data Index: 759991 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0379. Min Act: -0.1700

Data Index: 1372079 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0081. Min Act: -0.1700

Data Index: 190758 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0268. Min Act: -0.1700

Data Index: 931829 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0044. Min Act: -0.1700

Data Index: 562854 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 6.4499. Min Range: -6.4499

Max Act: 6.0080. Min Act: -0.1700

Data Index: 890085 (C4 (Web Text))

Max Activating Token Index: 1023