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

Dataset: Open Web Text

Neuron 2597 in Layer 2

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: 4.2946. Min Range: -4.2946

Max Act: 4.2946. Min Act: -0.1700

Data Index: 7412225 (Open Web Text)

Max Activating Token Index: 563

Text #1

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2359. Min Act: -0.1700

Data Index: 4680933 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2020. Min Act: -0.1700

Data Index: 5896215 (Open Web Text)

Max Activating Token Index: 631

Text #3

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2016. Min Act: -0.1700

Data Index: 2913110 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.2035. Min Act: -0.1700

Data Index: 5099785 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1639. Min Act: -0.1700

Data Index: 7736812 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1660. Min Act: -0.1700

Data Index: 4814452 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1704. Min Act: -0.1700

Data Index: 4535334 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1666. Min Act: -0.1700

Data Index: 5434722 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1896. Min Act: -0.1700

Data Index: 214418 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1693. Min Act: -0.1700

Data Index: 5003091 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1699. Min Act: -0.1700

Data Index: 8107830 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1338. Min Act: -0.1700

Data Index: 5306839 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1534. Min Act: -0.1700

Data Index: 4409387 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1325. Min Act: -0.1700

Data Index: 4411245 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1633. Min Act: -0.1700

Data Index: 3500069 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1485. Min Act: -0.1700

Data Index: 6769926 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1516. Min Act: -0.1700

Data Index: 2149998 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1206. Min Act: -0.1700

Data Index: 981802 (Open Web Text)

Max Activating Token Index: 818

Text #19

Max Range: 4.2946. Min Range: -4.2946

Max Act: 4.1354. Min Act: -0.1700

Data Index: 1889097 (Open Web Text)

Max Activating Token Index: 833