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

Dataset: Open Web Text

Neuron 1476 in Layer 4

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: 4.2393. Min Range: -4.2393

Max Act: 4.2393. Min Act: -0.1700

Data Index: 7551007 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1430. Min Act: -0.1700

Data Index: 6183632 (Open Web Text)

Max Activating Token Index: 846

Text #2

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1620. Min Act: -0.1700

Data Index: 2881697 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0970. Min Act: -0.1700

Data Index: 1287355 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1183. Min Act: -0.1700

Data Index: 5020402 (Open Web Text)

Max Activating Token Index: 671

Text #5

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0939. Min Act: -0.1700

Data Index: 8401846 (Open Web Text)

Max Activating Token Index: 856

Text #6

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0659. Min Act: -0.1700

Data Index: 2667198 (Open Web Text)

Max Activating Token Index: 713

Text #7

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0141. Min Act: -0.1700

Data Index: 2677176 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0479. Min Act: -0.1700

Data Index: 1092445 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0492. Min Act: -0.1700

Data Index: 6060501 (Open Web Text)

Max Activating Token Index: 738

Text #10

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0229. Min Act: -0.1700

Data Index: 1523170 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9824. Min Act: -0.1700

Data Index: 1978982 (Open Web Text)

Max Activating Token Index: 860

Text #12

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0196. Min Act: -0.1700

Data Index: 4339401 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0562. Min Act: -0.1700

Data Index: 8087207 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0141. Min Act: -0.1700

Data Index: 3514226 (Open Web Text)

Max Activating Token Index: 711

Text #15

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9859. Min Act: -0.1700

Data Index: 5356877 (Open Web Text)

Max Activating Token Index: 488

Text #16

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9386. Min Act: -0.1700

Data Index: 5718965 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9840. Min Act: -0.1700

Data Index: 5277708 (Open Web Text)

Max Activating Token Index: 744

Text #18

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9748. Min Act: -0.1700

Data Index: 4859537 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9681. Min Act: -0.1700

Data Index: 3008611 (Open Web Text)

Max Activating Token Index: 452