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

Dataset: Open Web Text

Neuron 2210 in Layer 3

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: 1.6953. Min Range: -1.6953

Max Act: 1.6935. Min Act: -0.1700

Data Index: 5770087 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6953. Min Act: -0.1700

Data Index: 780720 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6883. Min Act: -0.1700

Data Index: 3651371 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6866. Min Act: -0.1700

Data Index: 7448930 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6760. Min Act: -0.1700

Data Index: 5675963 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6723. Min Act: -0.1700

Data Index: 8112721 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6712. Min Act: -0.1700

Data Index: 509489 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6698. Min Act: -0.1700

Data Index: 7151745 (Open Web Text)

Max Activating Token Index: 539

Text #8

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6755. Min Act: -0.1700

Data Index: 4907850 (Open Web Text)

Max Activating Token Index: 684

Text #9

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6527. Min Act: -0.1700

Data Index: 3365538 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6723. Min Act: -0.1700

Data Index: 1983655 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6563. Min Act: -0.1700

Data Index: 2861758 (Open Web Text)

Max Activating Token Index: 87

Text #12

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6481. Min Act: -0.1700

Data Index: 4484756 (Open Web Text)

Max Activating Token Index: 263

Text #13

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6417. Min Act: -0.1700

Data Index: 3440605 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6320. Min Act: -0.1700

Data Index: 5714888 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6383. Min Act: -0.1700

Data Index: 7286441 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6344. Min Act: -0.1700

Data Index: 6276138 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6192. Min Act: -0.1700

Data Index: 1314360 (Open Web Text)

Max Activating Token Index: 759

Text #18

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6125. Min Act: -0.1700

Data Index: 6511653 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6287. Min Act: -0.1700

Data Index: 6109841 (Open Web Text)

Max Activating Token Index: 470