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

Dataset: Open Web Text

Neuron 2960 in Layer 5

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: 5.0073. Min Range: -5.0073

Max Act: 5.0073. Min Act: -0.1700

Data Index: 3610460 (Open Web Text)

Max Activating Token Index: 737

Text #1

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.9134. Min Act: -0.1700

Data Index: 6741490 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8536. Min Act: -0.1700

Data Index: 3975012 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8397. Min Act: -0.1700

Data Index: 8424407 (Open Web Text)

Max Activating Token Index: 918

Text #4

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8290. Min Act: -0.1700

Data Index: 8469989 (Open Web Text)

Max Activating Token Index: 192

Text #5

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8160. Min Act: -0.1700

Data Index: 6962127 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8104. Min Act: -0.1700

Data Index: 6747153 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7801. Min Act: -0.1700

Data Index: 8058544 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7890. Min Act: -0.1700

Data Index: 7573975 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7729. Min Act: -0.1700

Data Index: 6813522 (Open Web Text)

Max Activating Token Index: 1003

Text #10

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7994. Min Act: -0.1700

Data Index: 3355521 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7846. Min Act: -0.1700

Data Index: 5800113 (Open Web Text)

Max Activating Token Index: 720

Text #12

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7372. Min Act: -0.1700

Data Index: 5129084 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7401. Min Act: -0.1700

Data Index: 4928131 (Open Web Text)

Max Activating Token Index: 328

Text #14

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7171. Min Act: -0.1700

Data Index: 1106904 (Open Web Text)

Max Activating Token Index: 751

Text #15

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7067. Min Act: -0.1700

Data Index: 6730341 (Open Web Text)

Max Activating Token Index: 242

Text #16

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6990. Min Act: -0.1700

Data Index: 4284595 (Open Web Text)

Max Activating Token Index: 715

Text #17

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7311. Min Act: -0.1700

Data Index: 5657503 (Open Web Text)

Max Activating Token Index: 294

Text #18

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7137. Min Act: -0.1700

Data Index: 5941532 (Open Web Text)

Max Activating Token Index: 189

Text #19

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7047. Min Act: -0.1700

Data Index: 1401755 (Open Web Text)

Max Activating Token Index: 364