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

Dataset: Open Web Text

Neuron 1863 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: 5.3522. Min Range: -5.3522

Max Act: 5.3522. Min Act: -0.1700

Data Index: 3256317 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.3181. Min Act: -0.1700

Data Index: 6453131 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2882. Min Act: -0.1700

Data Index: 6792690 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.3061. Min Act: -0.1700

Data Index: 7477603 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2878. Min Act: -0.1700

Data Index: 5540647 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2385. Min Act: -0.1700

Data Index: 3832115 (Open Web Text)

Max Activating Token Index: 29

Text #6

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2392. Min Act: -0.1700

Data Index: 5659198 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1952. Min Act: -0.1700

Data Index: 6583249 (Open Web Text)

Max Activating Token Index: 830

Text #8

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2366. Min Act: -0.1700

Data Index: 2246457 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1933. Min Act: -0.1700

Data Index: 578676 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2129. Min Act: -0.1700

Data Index: 4166970 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1807. Min Act: -0.1700

Data Index: 7182744 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1740. Min Act: -0.1700

Data Index: 4445023 (Open Web Text)

Max Activating Token Index: 854

Text #13

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1638. Min Act: -0.1700

Data Index: 6999250 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2120. Min Act: -0.1700

Data Index: 1718750 (Open Web Text)

Max Activating Token Index: 880

Text #15

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1915. Min Act: -0.1700

Data Index: 8404575 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.2079. Min Act: -0.1700

Data Index: 7559893 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1433. Min Act: -0.1700

Data Index: 6829557 (Open Web Text)

Max Activating Token Index: 921

Text #18

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1658. Min Act: -0.1700

Data Index: 362166 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 5.3522. Min Range: -5.3522

Max Act: 5.1202. Min Act: -0.1700

Data Index: 7349368 (Open Web Text)

Max Activating Token Index: 629