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

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

Neuron 1912 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: 4.6150. Min Range: -4.6150

Max Act: 4.6150. Min Act: -0.1700

Data Index: 1505568 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.4976. Min Act: -0.1700

Data Index: 1336882 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.4001. Min Act: -0.1700

Data Index: 472789 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.4182. Min Act: -0.1700

Data Index: 1429806 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.4174. Min Act: -0.1700

Data Index: 1501117 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3917. Min Act: -0.1700

Data Index: 932556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3709. Min Act: -0.1700

Data Index: 1365014 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3561. Min Act: -0.1700

Data Index: 619332 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3412. Min Act: -0.1700

Data Index: 1606429 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3508. Min Act: -0.1700

Data Index: 1374729 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3458. Min Act: -0.1700

Data Index: 429170 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3399. Min Act: -0.1700

Data Index: 1357716 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3095. Min Act: -0.1700

Data Index: 352021 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3053. Min Act: -0.1700

Data Index: 1634889 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3000. Min Act: -0.1700

Data Index: 1529886 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.3024. Min Act: -0.1700

Data Index: 844128 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.2901. Min Act: -0.1700

Data Index: 1587417 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.2884. Min Act: -0.1700

Data Index: 1627131 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.2791. Min Act: -0.1700

Data Index: 1466420 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 4.6150. Min Range: -4.6150

Max Act: 4.2896. Min Act: -0.1700

Data Index: 1395978 (Python Code)

Max Activating Token Index: 1023