Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 546 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6159. Min Range: -5.6159

Max Act: 5.6159. Min Act: -0.1700

Data Index: 614748 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.6159. Min Range: -5.6159

Max Act: 5.2409. Min Act: -0.1700

Data Index: 988086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.6159. Min Range: -5.6159

Max Act: 5.1472. Min Act: -0.1700

Data Index: 1000378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.9284. Min Act: -0.1700

Data Index: 240024 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.6159. Min Range: -5.6159

Max Act: 5.1784. Min Act: -0.1700

Data Index: 1192186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.9284. Min Act: -0.1700

Data Index: 44139 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8972. Min Act: -0.1700

Data Index: 958750 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8659. Min Act: -0.1700

Data Index: 796830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8659. Min Act: -0.1700

Data Index: 186297 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8659. Min Act: -0.1700

Data Index: 856778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8347. Min Act: -0.1700

Data Index: 725755 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8034. Min Act: -0.1700

Data Index: 137498 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.8034. Min Act: -0.1700

Data Index: 298059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.7722. Min Act: -0.1700

Data Index: 745037 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.7409. Min Act: -0.1700

Data Index: 99837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.6784. Min Act: -0.1700

Data Index: 711714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.7097. Min Act: -0.1700

Data Index: 1201170 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.6784. Min Act: -0.1700

Data Index: 192453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.7097. Min Act: -0.1700

Data Index: 490842 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.6159. Min Range: -5.6159

Max Act: 4.6472. Min Act: -0.1700

Data Index: 629171 (C4 (Web Text))

Max Activating Token Index: 1023