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

Dataset: Open Web Text

Neuron 742 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: 3.3592. Min Range: -3.3592

Max Act: 3.3592. Min Act: -0.1700

Data Index: 2423098 (Open Web Text)

Max Activating Token Index: 58

Text #1

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.3303. Min Act: -0.1700

Data Index: 1525310 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2960. Min Act: -0.1700

Data Index: 851516 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2553. Min Act: -0.1699

Data Index: 1705300 (Open Web Text)

Max Activating Token Index: 318

Text #4

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2201. Min Act: -0.1700

Data Index: 6561267 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1182414 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1982. Min Act: -0.1700

Data Index: 4409282 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1783. Min Act: -0.1700

Data Index: 3960258 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1804. Min Act: -0.1700

Data Index: 588766 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1787. Min Act: -0.1696

Data Index: 1232125 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1847. Min Act: -0.1700

Data Index: 2118178 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1607. Min Act: -0.1700

Data Index: 1695999 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1513. Min Act: -0.1700

Data Index: 1115279 (Open Web Text)

Max Activating Token Index: 587

Text #13

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1541. Min Act: -0.1700

Data Index: 1709897 (Open Web Text)

Max Activating Token Index: 628

Text #14

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1538. Min Act: -0.1700

Data Index: 7245445 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1289. Min Act: -0.1700

Data Index: 5431191 (Open Web Text)

Max Activating Token Index: 316

Text #16

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1311. Min Act: -0.1700

Data Index: 5130019 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1331. Min Act: -0.1700

Data Index: 5872299 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1089. Min Act: -0.1700

Data Index: 3194568 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 3.3592. Min Range: -3.3592

Max Act: 3.1183. Min Act: -0.1700

Data Index: 2630383 (Open Web Text)

Max Activating Token Index: 462