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

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

Neuron 1450 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: 3.8263. Min Range: -3.8263

Max Act: 3.8263. Min Act: -0.1700

Data Index: 750097 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1610693 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1467400 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7712. Min Act: -0.1700

Data Index: 961 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7510. Min Act: -0.1700

Data Index: 1381477 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7390. Min Act: -0.1700

Data Index: 419420 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1383067 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7090. Min Act: -0.1700

Data Index: 1646374 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6982. Min Act: -0.1700

Data Index: 393169 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.7190. Min Act: -0.1700

Data Index: 1194884 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6961. Min Act: -0.1700

Data Index: 1131580 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6951. Min Act: -0.1700

Data Index: 1572463 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1597050 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6947. Min Act: -0.1700

Data Index: 1475678 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6919. Min Act: -0.1700

Data Index: 1651029 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6605. Min Act: -0.1700

Data Index: 503783 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6746. Min Act: -0.1700

Data Index: 1538338 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6707. Min Act: -0.1700

Data Index: 264681 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6363. Min Act: -0.1700

Data Index: 875816 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.6453. Min Act: -0.1700

Data Index: 1370147 (Python Code)

Max Activating Token Index: 1023