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

Dataset: Open Web Text

Neuron 2622 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: 3.2505. Min Range: -3.2505

Max Act: 3.2505. Min Act: -0.1700

Data Index: 6589964 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.2226. Min Act: -0.1700

Data Index: 2319765 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.2415. Min Act: -0.1700

Data Index: 5351164 (Open Web Text)

Max Activating Token Index: 745

Text #3

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.2091. Min Act: -0.1700

Data Index: 1971709 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.2041. Min Act: -0.1700

Data Index: 4314901 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1917. Min Act: -0.1700

Data Index: 3721718 (Open Web Text)

Max Activating Token Index: 229

Text #6

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1915. Min Act: -0.1700

Data Index: 4687308 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1948. Min Act: -0.1700

Data Index: 276671 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1743. Min Act: -0.1700

Data Index: 8671847 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1682. Min Act: -0.1700

Data Index: 4221469 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1640. Min Act: -0.1700

Data Index: 5182977 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1845. Min Act: -0.1700

Data Index: 1971708 (Open Web Text)

Max Activating Token Index: 188

Text #12

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1546. Min Act: -0.1700

Data Index: 4766126 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1476. Min Act: -0.1700

Data Index: 2971367 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1522. Min Act: -0.1700

Data Index: 1071620 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1366. Min Act: -0.1700

Data Index: 4740719 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1433. Min Act: -0.1700

Data Index: 1425098 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1568. Min Act: -0.1700

Data Index: 583259 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1557. Min Act: -0.1700

Data Index: 6720307 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1391. Min Act: -0.1700

Data Index: 1597583 (Open Web Text)

Max Activating Token Index: 722