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

Dataset: Open Web Text

Neuron 742 in Layer 2

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: 3.1068. Min Range: -3.1068

Max Act: 3.1068. Min Act: -0.1700

Data Index: 5106767 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 3.1068. Min Range: -3.1068

Max Act: 3.0167. Min Act: -0.1700

Data Index: 5907032 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 3.1068. Min Range: -3.1068

Max Act: 3.0036. Min Act: -0.1700

Data Index: 2869155 (Open Web Text)

Max Activating Token Index: 139

Text #3

Max Range: 3.1068. Min Range: -3.1068

Max Act: 3.0081. Min Act: -0.1700

Data Index: 5024806 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.9518. Min Act: -0.1700

Data Index: 4275081 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.9620. Min Act: -0.1700

Data Index: 8431796 (Open Web Text)

Max Activating Token Index: 156

Text #6

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.9046. Min Act: -0.1700

Data Index: 6359246 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.9037. Min Act: -0.1700

Data Index: 7471686 (Open Web Text)

Max Activating Token Index: 255

Text #8

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.9052. Min Act: -0.1700

Data Index: 3688845 (Open Web Text)

Max Activating Token Index: 387

Text #9

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.9086. Min Act: -0.1700

Data Index: 4962335 (Open Web Text)

Max Activating Token Index: 400

Text #10

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8786. Min Act: -0.1700

Data Index: 7659021 (Open Web Text)

Max Activating Token Index: 769

Text #11

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8576. Min Act: -0.1700

Data Index: 2296572 (Open Web Text)

Max Activating Token Index: 728

Text #12

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8765. Min Act: -0.1700

Data Index: 387396 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8495. Min Act: -0.1700

Data Index: 3259210 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8459. Min Act: -0.1700

Data Index: 6931236 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8534. Min Act: -0.1700

Data Index: 5716313 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8498. Min Act: -0.1700

Data Index: 7659028 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8616. Min Act: -0.1700

Data Index: 2989377 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8564. Min Act: -0.1700

Data Index: 2077360 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 3.1068. Min Range: -3.1068

Max Act: 2.8502. Min Act: -0.1700

Data Index: 764156 (Open Web Text)

Max Activating Token Index: 543