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

Dataset: Open Web Text

Neuron 1211 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: 5.3107. Min Range: -5.3107

Max Act: 5.3074. Min Act: -0.1700

Data Index: 5115999 (Open Web Text)

Max Activating Token Index: 200

Text #1

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1174499 (Open Web Text)

Max Activating Token Index: 957

Text #2

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.3066. Min Act: -0.1700

Data Index: 998848 (Open Web Text)

Max Activating Token Index: 377

Text #3

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2976. Min Act: -0.1700

Data Index: 4804993 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2611. Min Act: -0.1700

Data Index: 5562350 (Open Web Text)

Max Activating Token Index: 733

Text #5

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2928. Min Act: -0.1700

Data Index: 5776145 (Open Web Text)

Max Activating Token Index: 930

Text #6

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.3107. Min Act: -0.1700

Data Index: 8746006 (Open Web Text)

Max Activating Token Index: 798

Text #7

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2844. Min Act: -0.1700

Data Index: 4132911 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2799. Min Act: -0.1700

Data Index: 1359596 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2869. Min Act: -0.1700

Data Index: 5253576 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2581. Min Act: -0.1700

Data Index: 6623341 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2671. Min Act: -0.1700

Data Index: 6591758 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2294. Min Act: -0.1700

Data Index: 1308508 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2091. Min Act: -0.1700

Data Index: 5938237 (Open Web Text)

Max Activating Token Index: 635

Text #14

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2485. Min Act: -0.1700

Data Index: 256765 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2487. Min Act: -0.1700

Data Index: 3564445 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2806. Min Act: -0.1700

Data Index: 5464168 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2581. Min Act: -0.1700

Data Index: 2112911 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2798. Min Act: -0.1700

Data Index: 4927269 (Open Web Text)

Max Activating Token Index: 941

Text #19

Max Range: 5.3107. Min Range: -5.3107

Max Act: 5.2286. Min Act: -0.1700

Data Index: 5059443 (Open Web Text)

Max Activating Token Index: 842