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

Dataset: Open Web Text

Neuron 1444 in Layer 3

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: 4.7175. Min Range: -4.7175

Max Act: 4.7175. Min Act: -0.1700

Data Index: 3911679 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.6399. Min Act: -0.1700

Data Index: 2511895 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.5834. Min Act: -0.1700

Data Index: 3716825 (Open Web Text)

Max Activating Token Index: 28

Text #3

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.5599. Min Act: -0.1700

Data Index: 7604263 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.5706. Min Act: -0.1700

Data Index: 3709973 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.5309. Min Act: -0.1700

Data Index: 5806586 (Open Web Text)

Max Activating Token Index: 740

Text #6

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4626. Min Act: -0.1700

Data Index: 4843415 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4736. Min Act: -0.1700

Data Index: 2947563 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4408. Min Act: -0.1700

Data Index: 8449911 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4023. Min Act: -0.1700

Data Index: 8312491 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4084. Min Act: -0.1700

Data Index: 8757913 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4292. Min Act: -0.1700

Data Index: 6413656 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4236. Min Act: -0.1700

Data Index: 3295477 (Open Web Text)

Max Activating Token Index: 449

Text #13

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4079. Min Act: -0.1700

Data Index: 6867513 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.4030. Min Act: -0.1700

Data Index: 3801805 (Open Web Text)

Max Activating Token Index: 40

Text #15

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.3620. Min Act: -0.1700

Data Index: 2733603 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.3736. Min Act: -0.1700

Data Index: 628076 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.3758. Min Act: -0.1700

Data Index: 6736265 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.3773. Min Act: -0.1700

Data Index: 3051875 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.3828. Min Act: -0.1700

Data Index: 266500 (Open Web Text)

Max Activating Token Index: 282