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

Dataset: Open Web Text

Neuron 1040 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: 4.7145. Min Range: -4.7145

Max Act: 4.7145. Min Act: -0.1700

Data Index: 2857082 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.6144. Min Act: -0.1700

Data Index: 2173266 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5978. Min Act: -0.1700

Data Index: 8407572 (Open Web Text)

Max Activating Token Index: 786

Text #3

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5831. Min Act: -0.1700

Data Index: 7640949 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5762. Min Act: -0.1700

Data Index: 1671313 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5450. Min Act: -0.1700

Data Index: 8584412 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5488. Min Act: -0.1700

Data Index: 5830184 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5209. Min Act: -0.1700

Data Index: 6785164 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5147. Min Act: -0.1700

Data Index: 4108440 (Open Web Text)

Max Activating Token Index: 572

Text #9

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5204. Min Act: -0.1700

Data Index: 7481431 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5111. Min Act: -0.1700

Data Index: 8791579 (Open Web Text)

Max Activating Token Index: 710

Text #11

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5124. Min Act: -0.1700

Data Index: 3467096 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5222. Min Act: -0.1700

Data Index: 2714105 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5145. Min Act: -0.1700

Data Index: 2598449 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5102. Min Act: -0.1700

Data Index: 8698478 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5046. Min Act: -0.1700

Data Index: 4867587 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.4959. Min Act: -0.1700

Data Index: 934836 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.4844. Min Act: -0.1700

Data Index: 3871867 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5037. Min Act: -0.1700

Data Index: 1669146 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 4.7145. Min Range: -4.7145

Max Act: 4.5073. Min Act: -0.1700

Data Index: 8246471 (Open Web Text)

Max Activating Token Index: 502