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

Dataset: Open Web Text

Neuron 1912 in Layer 1

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: 1.9100. Min Range: -1.9100

Max Act: 1.9100. Min Act: -0.1700

Data Index: 1372802 (Open Web Text)

Max Activating Token Index: 535

Text #1

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8848. Min Act: -0.1700

Data Index: 1818929 (Open Web Text)

Max Activating Token Index: 122

Text #2

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8551. Min Act: -0.1700

Data Index: 2131565 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8320. Min Act: -0.1673

Data Index: 6765122 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8240. Min Act: -0.1700

Data Index: 252940 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8187. Min Act: -0.1700

Data Index: 8038374 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8175. Min Act: -0.1700

Data Index: 665899 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8162. Min Act: -0.1700

Data Index: 905744 (Open Web Text)

Max Activating Token Index: 1001

Text #8

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8124. Min Act: -0.1700

Data Index: 7986619 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.8094. Min Act: -0.1700

Data Index: 6641248 (Open Web Text)

Max Activating Token Index: 958

Text #10

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7996. Min Act: -0.1700

Data Index: 8778942 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7953. Min Act: -0.1699

Data Index: 70136 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7936. Min Act: -0.1700

Data Index: 6313421 (Open Web Text)

Max Activating Token Index: 767

Text #13

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7910. Min Act: -0.1700

Data Index: 358943 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7899. Min Act: -0.1700

Data Index: 6502204 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7916. Min Act: -0.1700

Data Index: 1036625 (Open Web Text)

Max Activating Token Index: 527

Text #16

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7846. Min Act: -0.1700

Data Index: 6028621 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7801. Min Act: -0.1700

Data Index: 6153137 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7735. Min Act: -0.1700

Data Index: 2941273 (Open Web Text)

Max Activating Token Index: 936

Text #19

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.7715. Min Act: -0.1700

Data Index: 3441363 (Open Web Text)

Max Activating Token Index: 665