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

Dataset: Open Web Text

Neuron 1688 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: 1.8984. Min Range: -1.8984

Max Act: 1.8984. Min Act: -0.1700

Data Index: 1107169 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8862. Min Act: -0.1700

Data Index: 1030666 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8561. Min Act: -0.1699

Data Index: 1469162 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8458. Min Act: -0.1700

Data Index: 2125824 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8547. Min Act: -0.1700

Data Index: 7367670 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8419. Min Act: -0.1700

Data Index: 498095 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8204. Min Act: -0.1700

Data Index: 8002812 (Open Web Text)

Max Activating Token Index: 867

Text #7

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8323. Min Act: -0.1700

Data Index: 6961081 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8080. Min Act: -0.1700

Data Index: 8764710 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8144. Min Act: -0.1700

Data Index: 8403556 (Open Web Text)

Max Activating Token Index: 284

Text #10

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8131. Min Act: -0.1700

Data Index: 6997337 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8054. Min Act: -0.1700

Data Index: 3752874 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.8014. Min Act: -0.1700

Data Index: 8286206 (Open Web Text)

Max Activating Token Index: 873

Text #13

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7902. Min Act: -0.1700

Data Index: 6570751 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7932. Min Act: -0.1700

Data Index: 2891673 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7817. Min Act: -0.1700

Data Index: 5019603 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7843. Min Act: -0.1700

Data Index: 897561 (Open Web Text)

Max Activating Token Index: 535

Text #17

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7937. Min Act: -0.1700

Data Index: 6604022 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7744. Min Act: -0.1700

Data Index: 8254575 (Open Web Text)

Max Activating Token Index: 551

Text #19

Max Range: 1.8984. Min Range: -1.8984

Max Act: 1.7617. Min Act: -0.1700

Data Index: 2959947 (Open Web Text)

Max Activating Token Index: 636