Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 911 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5470. Min Act: -0.1698

Data Index: 7582842 (Open Web Text)

Max Activating Token Index: 996

Text #1

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4974. Min Act: -0.1699

Data Index: 5617270 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5017. Min Act: -0.1700

Data Index: 3286343 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5130. Min Act: -0.1689

Data Index: 7582843 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5093. Min Act: -0.1700

Data Index: 3163207 (Open Web Text)

Max Activating Token Index: 290

Text #5

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4777. Min Act: -0.1700

Data Index: 474269 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4604. Min Act: -0.1700

Data Index: 3609016 (Open Web Text)

Max Activating Token Index: 849

Text #7

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4453. Min Act: -0.1687

Data Index: 7582844 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4276. Min Act: -0.1700

Data Index: 4159798 (Open Web Text)

Max Activating Token Index: 262

Text #9

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4407. Min Act: -0.1700

Data Index: 1212084 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4195. Min Act: -0.1688

Data Index: 2768304 (Open Web Text)

Max Activating Token Index: 364

Text #11

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4170. Min Act: -0.1700

Data Index: 3563362 (Open Web Text)

Max Activating Token Index: 449

Text #12

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4330. Min Act: -0.1700

Data Index: 7173280 (Open Web Text)

Max Activating Token Index: 530

Text #13

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4272. Min Act: -0.1699

Data Index: 7125267 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4201. Min Act: -0.1699

Data Index: 8559907 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4155. Min Act: -0.1695

Data Index: 920296 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4070. Min Act: -0.1698

Data Index: 5193499 (Open Web Text)

Max Activating Token Index: 93

Text #17

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4130. Min Act: -0.1700

Data Index: 7401549 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.3999. Min Act: -0.1685

Data Index: 2310754 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.4262. Min Act: -0.1700

Data Index: 5785041 (Open Web Text)

Max Activating Token Index: 1008