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

Dataset: Open Web Text

Neuron 632 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: 5.0529. Min Range: -5.0529

Max Act: 5.0529. Min Act: -0.1700

Data Index: 6606064 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.6833. Min Act: -0.1700

Data Index: 6404679 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.5781. Min Act: -0.1700

Data Index: 3013876 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.5225. Min Act: -0.1700

Data Index: 42284 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.2934. Min Act: -0.1700

Data Index: 6613454 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.2323. Min Act: -0.1700

Data Index: 4844027 (Open Web Text)

Max Activating Token Index: 55

Text #6

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.2328. Min Act: -0.1700

Data Index: 1631983 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.1885. Min Act: -0.1700

Data Index: 7184346 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.1994. Min Act: -0.1700

Data Index: 5317754 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.1981. Min Act: -0.1700

Data Index: 7479890 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.1414. Min Act: -0.1700

Data Index: 8254666 (Open Web Text)

Max Activating Token Index: 936

Text #11

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.1307. Min Act: -0.1700

Data Index: 4844028 (Open Web Text)

Max Activating Token Index: 923

Text #12

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0883. Min Act: -0.1700

Data Index: 3103777 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0557. Min Act: -0.1689

Data Index: 4490594 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0574. Min Act: -0.1699

Data Index: 1874225 (Open Web Text)

Max Activating Token Index: 245

Text #15

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0694. Min Act: -0.1700

Data Index: 3058895 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0654. Min Act: -0.1700

Data Index: 8343841 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0456. Min Act: -0.1700

Data Index: 8036328 (Open Web Text)

Max Activating Token Index: 874

Text #18

Max Range: 5.0529. Min Range: -5.0529

Max Act: 3.9931. Min Act: -0.1700

Data Index: 6433270 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 5.0529. Min Range: -5.0529

Max Act: 4.0494. Min Act: -0.1700

Data Index: 3913249 (Open Web Text)

Max Activating Token Index: 702