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

Dataset: Open Web Text

Neuron 2131 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: 4.4131. Min Range: -4.4131

Max Act: 4.4131. Min Act: -0.1700

Data Index: 2399166 (Open Web Text)

Max Activating Token Index: 615

Text #1

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.3584. Min Act: -0.1700

Data Index: 5890372 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.2772. Min Act: -0.1700

Data Index: 3690936 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.2969. Min Act: -0.1700

Data Index: 2660101 (Open Web Text)

Max Activating Token Index: 181

Text #4

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.2166. Min Act: -0.1700

Data Index: 5443672 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.3106. Min Act: -0.1700

Data Index: 7075743 (Open Web Text)

Max Activating Token Index: 339

Text #6

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.2641. Min Act: -0.1700

Data Index: 7367356 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1593. Min Act: -0.1700

Data Index: 3666985 (Open Web Text)

Max Activating Token Index: 234

Text #8

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1696. Min Act: -0.1700

Data Index: 3105245 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1409. Min Act: -0.1700

Data Index: 124039 (Open Web Text)

Max Activating Token Index: 402

Text #10

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1923. Min Act: -0.1700

Data Index: 234370 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.3394. Min Act: -0.1700

Data Index: 8779747 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1831. Min Act: -0.1700

Data Index: 1578794 (Open Web Text)

Max Activating Token Index: 81

Text #13

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1108. Min Act: -0.1700

Data Index: 3512241 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.0189. Min Act: -0.1700

Data Index: 1982808 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.2016. Min Act: -0.1700

Data Index: 5771336 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.0947. Min Act: -0.1700

Data Index: 6067861 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1125. Min Act: -0.1700

Data Index: 1351560 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.0600. Min Act: -0.1700

Data Index: 1704537 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 4.4131. Min Range: -4.4131

Max Act: 4.1081. Min Act: -0.1700

Data Index: 3679547 (Open Web Text)

Max Activating Token Index: 257