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

Dataset: Open Web Text

Neuron 619 in Layer 4

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: 4.0620. Min Range: -4.0620

Max Act: 4.0620. Min Act: -0.1700

Data Index: 5885797 (Open Web Text)

Max Activating Token Index: 171

Text #1

Max Range: 4.0620. Min Range: -4.0620

Max Act: 4.0211. Min Act: -0.1700

Data Index: 5992037 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9509. Min Act: -0.1700

Data Index: 141341 (Open Web Text)

Max Activating Token Index: 977

Text #3

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8990. Min Act: -0.1700

Data Index: 8185718 (Open Web Text)

Max Activating Token Index: 769

Text #4

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8858. Min Act: -0.1700

Data Index: 6769452 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9046. Min Act: -0.1700

Data Index: 3484019 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9405. Min Act: -0.1700

Data Index: 7365321 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8975. Min Act: -0.1700

Data Index: 7641943 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8896. Min Act: -0.1700

Data Index: 1872257 (Open Web Text)

Max Activating Token Index: 916

Text #9

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8604. Min Act: -0.1700

Data Index: 3233242 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1971313 (Open Web Text)

Max Activating Token Index: 855

Text #11

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8597. Min Act: -0.1700

Data Index: 5619291 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8409. Min Act: -0.1700

Data Index: 3763475 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8403. Min Act: -0.1700

Data Index: 625132 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8495. Min Act: -0.1700

Data Index: 1852408 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8544. Min Act: -0.1700

Data Index: 6596338 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8349. Min Act: -0.1700

Data Index: 2868776 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8318. Min Act: -0.1700

Data Index: 5225933 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8183. Min Act: -0.1700

Data Index: 5000856 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.7857. Min Act: -0.1700

Data Index: 6077188 (Open Web Text)

Max Activating Token Index: 947