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

Dataset: Open Web Text

Neuron 868 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: 4.6405. Min Range: -4.6405

Max Act: 4.6405. Min Act: -0.1700

Data Index: 8173016 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.6337. Min Act: -0.1700

Data Index: 6995789 (Open Web Text)

Max Activating Token Index: 932

Text #2

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5966. Min Act: -0.1700

Data Index: 1689116 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5819. Min Act: -0.1700

Data Index: 1983550 (Open Web Text)

Max Activating Token Index: 475

Text #4

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5519. Min Act: -0.1700

Data Index: 6948973 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5683. Min Act: -0.1700

Data Index: 5289415 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5242. Min Act: -0.1700

Data Index: 5524358 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5318. Min Act: -0.1700

Data Index: 6496429 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5250. Min Act: -0.1700

Data Index: 3209238 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5228. Min Act: -0.1700

Data Index: 6750406 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4827. Min Act: -0.1700

Data Index: 4635399 (Open Web Text)

Max Activating Token Index: 795

Text #11

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4909. Min Act: -0.1700

Data Index: 4172568 (Open Web Text)

Max Activating Token Index: 583

Text #12

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5113. Min Act: -0.1700

Data Index: 3778458 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5098. Min Act: -0.1700

Data Index: 4111159 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5112. Min Act: -0.1700

Data Index: 1941057 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4634. Min Act: -0.1700

Data Index: 4569347 (Open Web Text)

Max Activating Token Index: 169

Text #16

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4683. Min Act: -0.1700

Data Index: 265907 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4750. Min Act: -0.1700

Data Index: 4482596 (Open Web Text)

Max Activating Token Index: 771

Text #18

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4641. Min Act: -0.1700

Data Index: 5524360 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.4574. Min Act: -0.1700

Data Index: 2726923 (Open Web Text)

Max Activating Token Index: 21