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

Dataset: Open Web Text

Neuron 306 in Layer 6

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: 7.8677. Min Range: -7.8677

Max Act: 7.8677. Min Act: -0.1700

Data Index: 2873590 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.7677. Min Act: -0.1700

Data Index: 882718 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.6080. Min Act: -0.1700

Data Index: 1595463 (Open Web Text)

Max Activating Token Index: 885

Text #3

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.4447. Min Act: -0.1700

Data Index: 2109211 (Open Web Text)

Max Activating Token Index: 884

Text #4

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.4108. Min Act: -0.1700

Data Index: 3058771 (Open Web Text)

Max Activating Token Index: 226

Text #5

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.3105. Min Act: -0.1700

Data Index: 1110465 (Open Web Text)

Max Activating Token Index: 561

Text #6

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.2406. Min Act: -0.1700

Data Index: 1042433 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.2631. Min Act: -0.1700

Data Index: 3757789 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.2428. Min Act: -0.1700

Data Index: 8427358 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.2468. Min Act: -0.1700

Data Index: 5667980 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.1955. Min Act: -0.1700

Data Index: 5965340 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.0823. Min Act: -0.1700

Data Index: 5644527 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.1845. Min Act: -0.1700

Data Index: 3223929 (Open Web Text)

Max Activating Token Index: 141

Text #13

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.1194. Min Act: -0.1700

Data Index: 8455525 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.0244. Min Act: -0.1700

Data Index: 4368002 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.0543. Min Act: -0.1700

Data Index: 2485518 (Open Web Text)

Max Activating Token Index: 318

Text #16

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.0169. Min Act: -0.1700

Data Index: 6217609 (Open Web Text)

Max Activating Token Index: 1005

Text #17

Max Range: 7.8677. Min Range: -7.8677

Max Act: 7.0350. Min Act: -0.1700

Data Index: 2947036 (Open Web Text)

Max Activating Token Index: 738

Text #18

Max Range: 7.8677. Min Range: -7.8677

Max Act: 6.9478. Min Act: -0.1700

Data Index: 4290463 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 7.8677. Min Range: -7.8677

Max Act: 6.9851. Min Act: -0.1700

Data Index: 4804495 (Open Web Text)

Max Activating Token Index: 364