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

Dataset: Open Web Text

Neuron 2206 in Layer 4

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: 3.1763. Min Range: -3.1763

Max Act: 3.1763. Min Act: -0.1700

Data Index: 1411605 (Open Web Text)

Max Activating Token Index: 660

Text #1

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.1213. Min Act: -0.1700

Data Index: 3427896 (Open Web Text)

Max Activating Token Index: 486

Text #2

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.1069. Min Act: -0.1700

Data Index: 1322984 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0817. Min Act: -0.1700

Data Index: 1800686 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0568. Min Act: -0.1700

Data Index: 3783490 (Open Web Text)

Max Activating Token Index: 231

Text #5

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0383. Min Act: -0.1700

Data Index: 7658975 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0665. Min Act: -0.1700

Data Index: 344841 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0572. Min Act: -0.1700

Data Index: 1416369 (Open Web Text)

Max Activating Token Index: 139

Text #8

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0091. Min Act: -0.1700

Data Index: 1610311 (Open Web Text)

Max Activating Token Index: 848

Text #9

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0390. Min Act: -0.1700

Data Index: 1422189 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0529. Min Act: -0.1700

Data Index: 4129234 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0011. Min Act: -0.1700

Data Index: 1003843 (Open Web Text)

Max Activating Token Index: 885

Text #12

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0162. Min Act: -0.1700

Data Index: 6303294 (Open Web Text)

Max Activating Token Index: 227

Text #13

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0089. Min Act: -0.1700

Data Index: 6012233 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0076. Min Act: -0.1700

Data Index: 4325142 (Open Web Text)

Max Activating Token Index: 812

Text #15

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0150. Min Act: -0.1700

Data Index: 3853765 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0206. Min Act: -0.1700

Data Index: 2788143 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 3.1763. Min Range: -3.1763

Max Act: 2.9894. Min Act: -0.1700

Data Index: 7884185 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0093. Min Act: -0.1700

Data Index: 7082692 (Open Web Text)

Max Activating Token Index: 127

Text #19

Max Range: 3.1763. Min Range: -3.1763

Max Act: 3.0142. Min Act: -0.1700

Data Index: 8358607 (Open Web Text)

Max Activating Token Index: 559