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

Dataset: Open Web Text

Neuron 1693 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: 3.9592. Min Range: -3.9592

Max Act: 3.9592. Min Act: -0.1700

Data Index: 6561243 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.8835. Min Act: -0.1700

Data Index: 8519526 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.8943. Min Act: -0.1700

Data Index: 7776623 (Open Web Text)

Max Activating Token Index: 307

Text #3

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.8658. Min Act: -0.1700

Data Index: 1307696 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.8682. Min Act: -0.1700

Data Index: 2098255 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.8743. Min Act: -0.1700

Data Index: 5007877 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7917. Min Act: -0.1700

Data Index: 7767127 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.8050. Min Act: -0.1700

Data Index: 6443402 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7105. Min Act: -0.1700

Data Index: 2832659 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7499. Min Act: -0.1700

Data Index: 1193292 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7576. Min Act: -0.1700

Data Index: 4405716 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7803. Min Act: -0.1700

Data Index: 1366216 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7831. Min Act: -0.1700

Data Index: 2284215 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7343. Min Act: -0.1700

Data Index: 177534 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7143. Min Act: -0.1700

Data Index: 3054632 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7258. Min Act: -0.1700

Data Index: 5829781 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7092. Min Act: -0.1700

Data Index: 6595007 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7106. Min Act: -0.1700

Data Index: 3206797 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7270. Min Act: -0.1700

Data Index: 7389431 (Open Web Text)

Max Activating Token Index: 1000

Text #19

Max Range: 3.9592. Min Range: -3.9592

Max Act: 3.7270. Min Act: -0.1700

Data Index: 6319848 (Open Web Text)

Max Activating Token Index: 449