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

Dataset: Open Web Text

Neuron 2462 in Layer 6

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: 5.7050. Min Range: -5.7050

Max Act: 5.7050. Min Act: -0.1700

Data Index: 6645509 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.6064. Min Act: -0.1700

Data Index: 6101203 (Open Web Text)

Max Activating Token Index: 672

Text #2

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.5666. Min Act: -0.1700

Data Index: 2150080 (Open Web Text)

Max Activating Token Index: 515

Text #3

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4717. Min Act: -0.1700

Data Index: 5278192 (Open Web Text)

Max Activating Token Index: 331

Text #4

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4980. Min Act: -0.1700

Data Index: 7098383 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4468. Min Act: -0.1700

Data Index: 8237967 (Open Web Text)

Max Activating Token Index: 341

Text #6

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4417. Min Act: -0.1700

Data Index: 5285279 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4460. Min Act: -0.1700

Data Index: 4348470 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4028. Min Act: -0.1700

Data Index: 1774423 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3795. Min Act: -0.1700

Data Index: 1792059 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3606. Min Act: -0.1700

Data Index: 830061 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4185. Min Act: -0.1700

Data Index: 4237316 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3824. Min Act: -0.1700

Data Index: 2535844 (Open Web Text)

Max Activating Token Index: 909

Text #13

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.4245. Min Act: -0.1700

Data Index: 1558302 (Open Web Text)

Max Activating Token Index: 842

Text #14

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3674. Min Act: -0.1700

Data Index: 6595113 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3537. Min Act: -0.1700

Data Index: 3215991 (Open Web Text)

Max Activating Token Index: 369

Text #16

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3646. Min Act: -0.1700

Data Index: 2541926 (Open Web Text)

Max Activating Token Index: 268

Text #17

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3915. Min Act: -0.1700

Data Index: 6520784 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3859. Min Act: -0.1700

Data Index: 1935662 (Open Web Text)

Max Activating Token Index: 976

Text #19

Max Range: 5.7050. Min Range: -5.7050

Max Act: 5.3503. Min Act: -0.1700

Data Index: 734355 (Open Web Text)

Max Activating Token Index: 842