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

Dataset: Open Web Text

Neuron 546 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: 3.1077. Min Range: -3.1077

Max Act: 3.0947. Min Act: -0.1700

Data Index: 6548712 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0893. Min Act: -0.1700

Data Index: 6196458 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0970. Min Act: -0.1700

Data Index: 8403250 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.1004. Min Act: -0.1700

Data Index: 7046066 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0851. Min Act: -0.1700

Data Index: 4001377 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0870. Min Act: -0.1700

Data Index: 8156342 (Open Web Text)

Max Activating Token Index: 570

Text #6

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.1077. Min Act: -0.1700

Data Index: 1193844 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0703. Min Act: -0.1700

Data Index: 4309230 (Open Web Text)

Max Activating Token Index: 149

Text #8

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0916. Min Act: -0.1700

Data Index: 7184941 (Open Web Text)

Max Activating Token Index: 226

Text #9

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0698. Min Act: -0.1700

Data Index: 1630068 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0611. Min Act: -0.1700

Data Index: 3554156 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0601. Min Act: -0.1700

Data Index: 7467724 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0617. Min Act: -0.1700

Data Index: 5746771 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0673. Min Act: -0.1700

Data Index: 1719 (Open Web Text)

Max Activating Token Index: 237

Text #14

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0604. Min Act: -0.1700

Data Index: 4570254 (Open Web Text)

Max Activating Token Index: 871

Text #15

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0406. Min Act: -0.1700

Data Index: 8106237 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0367. Min Act: -0.1700

Data Index: 546438 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0414. Min Act: -0.1700

Data Index: 536352 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0337. Min Act: -0.1700

Data Index: 73198 (Open Web Text)

Max Activating Token Index: 949

Text #19

Max Range: 3.1077. Min Range: -3.1077

Max Act: 3.0483. Min Act: -0.1700

Data Index: 1972715 (Open Web Text)

Max Activating Token Index: 512