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

Dataset: Open Web Text

Neuron 1883 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: 2.9717. Min Range: -2.9717

Max Act: 2.9717. Min Act: -0.1700

Data Index: 7727907 (Open Web Text)

Max Activating Token Index: 576

Text #1

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.9064. Min Act: -0.1700

Data Index: 7162233 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.9313. Min Act: -0.1700

Data Index: 6942586 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.9032. Min Act: -0.1700

Data Index: 5554601 (Open Web Text)

Max Activating Token Index: 693

Text #4

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8766. Min Act: -0.1700

Data Index: 3915669 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8646. Min Act: -0.1700

Data Index: 5405803 (Open Web Text)

Max Activating Token Index: 418

Text #6

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8496. Min Act: -0.1700

Data Index: 5950576 (Open Web Text)

Max Activating Token Index: 140

Text #7

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8420. Min Act: -0.1700

Data Index: 2529972 (Open Web Text)

Max Activating Token Index: 95

Text #8

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8515. Min Act: -0.1700

Data Index: 6018596 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8399. Min Act: -0.1700

Data Index: 3686468 (Open Web Text)

Max Activating Token Index: 450

Text #10

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8278. Min Act: -0.1700

Data Index: 4930277 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8130. Min Act: -0.1700

Data Index: 260582 (Open Web Text)

Max Activating Token Index: 804

Text #12

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7888. Min Act: -0.1700

Data Index: 1356750 (Open Web Text)

Max Activating Token Index: 830

Text #13

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.8028. Min Act: -0.1700

Data Index: 919385 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7657. Min Act: -0.1700

Data Index: 4910324 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7871. Min Act: -0.1700

Data Index: 4871806 (Open Web Text)

Max Activating Token Index: 504

Text #16

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7749. Min Act: -0.1700

Data Index: 7462424 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7895. Min Act: -0.1700

Data Index: 5694262 (Open Web Text)

Max Activating Token Index: 638

Text #18

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7931. Min Act: -0.1700

Data Index: 1344324 (Open Web Text)

Max Activating Token Index: 460

Text #19

Max Range: 2.9717. Min Range: -2.9717

Max Act: 2.7450. Min Act: -0.1700

Data Index: 3246199 (Open Web Text)

Max Activating Token Index: 408