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

Dataset: Open Web Text

Neuron 123 in Layer 3

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: 3.3227. Min Range: -3.3227

Max Act: 3.3227. Min Act: -0.1700

Data Index: 6805267 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.2537. Min Act: -0.1700

Data Index: 7129773 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.2185. Min Act: -0.1700

Data Index: 4445768 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.2062. Min Act: -0.1700

Data Index: 5869600 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1674. Min Act: -0.1700

Data Index: 2692707 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1803. Min Act: -0.1700

Data Index: 1492831 (Open Web Text)

Max Activating Token Index: 923

Text #6

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1897. Min Act: -0.1700

Data Index: 3904435 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1709. Min Act: -0.1700

Data Index: 7999428 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1587. Min Act: -0.1700

Data Index: 8241919 (Open Web Text)

Max Activating Token Index: 649

Text #9

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1532. Min Act: -0.1700

Data Index: 700062 (Open Web Text)

Max Activating Token Index: 779

Text #10

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1535. Min Act: -0.1700

Data Index: 4683701 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1670. Min Act: -0.1700

Data Index: 2719392 (Open Web Text)

Max Activating Token Index: 122

Text #12

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1594. Min Act: -0.1700

Data Index: 7470609 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1450. Min Act: -0.1700

Data Index: 3347358 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1356. Min Act: -0.1700

Data Index: 3904436 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1375. Min Act: -0.1700

Data Index: 2055728 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1481. Min Act: -0.1700

Data Index: 2005976 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1306. Min Act: -0.1700

Data Index: 5908599 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1158. Min Act: -0.1700

Data Index: 1491875 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.1290. Min Act: -0.1700

Data Index: 7541955 (Open Web Text)

Max Activating Token Index: 417