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

Dataset: Open Web Text

Neuron 1253 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: 3.3177. Min Range: -3.3177

Max Act: 3.3177. Min Act: -0.1700

Data Index: 6602410 (Open Web Text)

Max Activating Token Index: 53

Text #1

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2398. Min Act: -0.1700

Data Index: 7435537 (Open Web Text)

Max Activating Token Index: 841

Text #2

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2277. Min Act: -0.1700

Data Index: 2813219 (Open Web Text)

Max Activating Token Index: 737

Text #3

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2044. Min Act: -0.1700

Data Index: 2764521 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2072. Min Act: -0.1700

Data Index: 1407816 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2119. Min Act: -0.1700

Data Index: 1556582 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1918. Min Act: -0.1700

Data Index: 1293062 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1457. Min Act: -0.1700

Data Index: 1442623 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1634. Min Act: -0.1700

Data Index: 4714909 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1565. Min Act: -0.1700

Data Index: 5917170 (Open Web Text)

Max Activating Token Index: 202

Text #10

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1733. Min Act: -0.1700

Data Index: 1724003 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1645. Min Act: -0.1700

Data Index: 318679 (Open Web Text)

Max Activating Token Index: 538

Text #12

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1680. Min Act: -0.1700

Data Index: 753796 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1616. Min Act: -0.1700

Data Index: 2566173 (Open Web Text)

Max Activating Token Index: 236

Text #14

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1335. Min Act: -0.1700

Data Index: 4306463 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1465. Min Act: -0.1700

Data Index: 7803455 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1344. Min Act: -0.1700

Data Index: 6663647 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1258. Min Act: -0.1700

Data Index: 6870809 (Open Web Text)

Max Activating Token Index: 810

Text #18

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1396. Min Act: -0.1700

Data Index: 749401 (Open Web Text)

Max Activating Token Index: 165

Text #19

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1368. Min Act: -0.1700

Data Index: 4399342 (Open Web Text)

Max Activating Token Index: 372