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

Dataset: Open Web Text

Neuron 1784 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: 3.3190. Min Range: -3.3190

Max Act: 3.3190. Min Act: -0.1700

Data Index: 2513696 (Open Web Text)

Max Activating Token Index: 584

Text #1

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.2797. Min Act: -0.1700

Data Index: 2749858 (Open Web Text)

Max Activating Token Index: 108

Text #2

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1629. Min Act: -0.1700

Data Index: 862620 (Open Web Text)

Max Activating Token Index: 907

Text #3

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.2011. Min Act: -0.1700

Data Index: 2711672 (Open Web Text)

Max Activating Token Index: 493

Text #4

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1585. Min Act: -0.1700

Data Index: 134453 (Open Web Text)

Max Activating Token Index: 105

Text #5

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1475. Min Act: -0.1700

Data Index: 5661578 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1618. Min Act: -0.1700

Data Index: 7663192 (Open Web Text)

Max Activating Token Index: 254

Text #7

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1664. Min Act: -0.1700

Data Index: 1074581 (Open Web Text)

Max Activating Token Index: 422

Text #8

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1272. Min Act: -0.1700

Data Index: 3569889 (Open Web Text)

Max Activating Token Index: 520

Text #9

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1377. Min Act: -0.1700

Data Index: 2261149 (Open Web Text)

Max Activating Token Index: 595

Text #10

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1443. Min Act: -0.1700

Data Index: 5409427 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1265. Min Act: -0.1700

Data Index: 6826521 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1471. Min Act: -0.1700

Data Index: 5765074 (Open Web Text)

Max Activating Token Index: 847

Text #13

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1386. Min Act: -0.1700

Data Index: 6055743 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1399. Min Act: -0.1700

Data Index: 1581116 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1039. Min Act: -0.1700

Data Index: 5034023 (Open Web Text)

Max Activating Token Index: 475

Text #16

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1396. Min Act: -0.1700

Data Index: 743313 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1061. Min Act: -0.1700

Data Index: 6838949 (Open Web Text)

Max Activating Token Index: 807

Text #18

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1473. Min Act: -0.1700

Data Index: 6007260 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 3.3190. Min Range: -3.3190

Max Act: 3.1063. Min Act: -0.1700

Data Index: 4107899 (Open Web Text)

Max Activating Token Index: 80