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

Dataset: Open Web Text

Neuron 2241 in Layer 0

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: 3.1057. Min Range: -3.1057

Max Act: 3.1057. Min Act: -0.1700

Data Index: 5060155 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0887. Min Act: -0.1700

Data Index: 6948859 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0671. Min Act: -0.1700

Data Index: 1193152 (Open Web Text)

Max Activating Token Index: 905

Text #3

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0605. Min Act: -0.1700

Data Index: 48697 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0544. Min Act: -0.1700

Data Index: 5359020 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0136. Min Act: -0.1700

Data Index: 4963923 (Open Web Text)

Max Activating Token Index: 768

Text #6

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0066. Min Act: -0.1700

Data Index: 321333 (Open Web Text)

Max Activating Token Index: 158

Text #7

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0176. Min Act: -0.1700

Data Index: 6812324 (Open Web Text)

Max Activating Token Index: 604

Text #8

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0052. Min Act: -0.1700

Data Index: 5525223 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0004. Min Act: -0.1700

Data Index: 2874463 (Open Web Text)

Max Activating Token Index: 920

Text #10

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9950. Min Act: -0.1700

Data Index: 2620075 (Open Web Text)

Max Activating Token Index: 384

Text #11

Max Range: 3.1057. Min Range: -3.1057

Max Act: 3.0043. Min Act: -0.1700

Data Index: 5678435 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9914. Min Act: -0.1700

Data Index: 3781489 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9872. Min Act: -0.1700

Data Index: 4596363 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9884. Min Act: -0.1700

Data Index: 8046492 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9943. Min Act: -0.1700

Data Index: 7531054 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9763. Min Act: -0.1700

Data Index: 2332717 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9645. Min Act: -0.1700

Data Index: 4242353 (Open Web Text)

Max Activating Token Index: 825

Text #18

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9772. Min Act: -0.1700

Data Index: 2047323 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 3.1057. Min Range: -3.1057

Max Act: 2.9756. Min Act: -0.1700

Data Index: 3888939 (Open Web Text)

Max Activating Token Index: 1021