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

Dataset: Open Web Text

Neuron 2961 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: 4.3868. Min Range: -4.3868

Max Act: 4.3868. Min Act: -0.1700

Data Index: 3848899 (Open Web Text)

Max Activating Token Index: 872

Text #1

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2862. Min Act: -0.1700

Data Index: 6306602 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2808. Min Act: -0.1700

Data Index: 412384 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2385. Min Act: -0.1700

Data Index: 6774296 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2171. Min Act: -0.1700

Data Index: 1041185 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2601. Min Act: -0.1700

Data Index: 3845752 (Open Web Text)

Max Activating Token Index: 779

Text #6

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2612. Min Act: -0.1700

Data Index: 4365235 (Open Web Text)

Max Activating Token Index: 1006

Text #7

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2341. Min Act: -0.1700

Data Index: 3019753 (Open Web Text)

Max Activating Token Index: 972

Text #8

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2210. Min Act: -0.1700

Data Index: 7340202 (Open Web Text)

Max Activating Token Index: 535

Text #9

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2053. Min Act: -0.1700

Data Index: 3947371 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1853. Min Act: -0.1700

Data Index: 3559875 (Open Web Text)

Max Activating Token Index: 811

Text #11

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1880. Min Act: -0.1700

Data Index: 8520437 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1801. Min Act: -0.1700

Data Index: 3581258 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1568. Min Act: -0.1700

Data Index: 1158428 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1678. Min Act: -0.1700

Data Index: 851389 (Open Web Text)

Max Activating Token Index: 883

Text #15

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1663. Min Act: -0.1700

Data Index: 6693167 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1534. Min Act: -0.1700

Data Index: 4508636 (Open Web Text)

Max Activating Token Index: 797

Text #17

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1662. Min Act: -0.1700

Data Index: 2972983 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1292. Min Act: -0.1700

Data Index: 5937692 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1588. Min Act: -0.1700

Data Index: 542299 (Open Web Text)

Max Activating Token Index: 1013