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

Dataset: Open Web Text

Neuron 2839 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: 3.3292. Min Range: -3.3292

Max Act: 3.3292. Min Act: -0.1700

Data Index: 7012226 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.3198. Min Act: -0.1700

Data Index: 7481115 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.3024. Min Act: -0.1700

Data Index: 5216458 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2625. Min Act: -0.1700

Data Index: 1157961 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2594. Min Act: -0.1700

Data Index: 6719694 (Open Web Text)

Max Activating Token Index: 344

Text #5

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2315. Min Act: -0.1700

Data Index: 6914590 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2053. Min Act: -0.1700

Data Index: 1928788 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2118. Min Act: -0.1700

Data Index: 4602650 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1872. Min Act: -0.1700

Data Index: 5063353 (Open Web Text)

Max Activating Token Index: 982

Text #9

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2232. Min Act: -0.1700

Data Index: 8820954 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2038. Min Act: -0.1700

Data Index: 478234 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1887971 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.2034. Min Act: -0.1700

Data Index: 7481374 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1894. Min Act: -0.1700

Data Index: 258550 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1803. Min Act: -0.1700

Data Index: 465867 (Open Web Text)

Max Activating Token Index: 78

Text #15

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1869. Min Act: -0.1700

Data Index: 7538918 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1734. Min Act: -0.1700

Data Index: 6050580 (Open Web Text)

Max Activating Token Index: 198

Text #17

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1840. Min Act: -0.1700

Data Index: 3518559 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1788. Min Act: -0.1700

Data Index: 2710278 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.3292. Min Range: -3.3292

Max Act: 3.1651. Min Act: -0.1700

Data Index: 4310059 (Open Web Text)

Max Activating Token Index: 894