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

Dataset: Open Web Text

Neuron 2168 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: 3.7912. Min Range: -3.7912

Max Act: 3.7912. Min Act: -0.1700

Data Index: 3543299 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.7581. Min Act: -0.1700

Data Index: 1809835 (Open Web Text)

Max Activating Token Index: 762

Text #2

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6807. Min Act: -0.1700

Data Index: 2858403 (Open Web Text)

Max Activating Token Index: 115

Text #3

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6863. Min Act: -0.1700

Data Index: 6838634 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6821. Min Act: -0.1700

Data Index: 5483751 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6128. Min Act: -0.1700

Data Index: 7272288 (Open Web Text)

Max Activating Token Index: 777

Text #6

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6374. Min Act: -0.1700

Data Index: 4852411 (Open Web Text)

Max Activating Token Index: 658

Text #7

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6369. Min Act: -0.1700

Data Index: 2508081 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6316. Min Act: -0.1700

Data Index: 6688516 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6422. Min Act: -0.1700

Data Index: 1352071 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6022. Min Act: -0.1700

Data Index: 3358383 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5999. Min Act: -0.1700

Data Index: 197936 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5823. Min Act: -0.1700

Data Index: 18210 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5880. Min Act: -0.1700

Data Index: 5748478 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6180. Min Act: -0.1700

Data Index: 588514 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5812. Min Act: -0.1700

Data Index: 6229831 (Open Web Text)

Max Activating Token Index: 101

Text #16

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5835. Min Act: -0.1700

Data Index: 1446519 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.6033. Min Act: -0.1700

Data Index: 6660456 (Open Web Text)

Max Activating Token Index: 943

Text #18

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5929. Min Act: -0.1700

Data Index: 1048100 (Open Web Text)

Max Activating Token Index: 983

Text #19

Max Range: 3.7912. Min Range: -3.7912

Max Act: 3.5820. Min Act: -0.1700

Data Index: 4319472 (Open Web Text)

Max Activating Token Index: 694