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

Dataset: Open Web Text

Neuron 1926 in Layer 1

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: 2.1016. Min Range: -2.1016

Max Act: 2.1016. Min Act: -0.1700

Data Index: 6396137 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0613. Min Act: -0.1700

Data Index: 7710164 (Open Web Text)

Max Activating Token Index: 475

Text #2

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0601. Min Act: -0.1700

Data Index: 6735749 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0276. Min Act: -0.1700

Data Index: 6621807 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0327. Min Act: -0.1700

Data Index: 7159539 (Open Web Text)

Max Activating Token Index: 340

Text #5

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0167. Min Act: -0.1700

Data Index: 4097229 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 2.1016. Min Range: -2.1016

Max Act: 2.0170. Min Act: -0.1700

Data Index: 3799638 (Open Web Text)

Max Activating Token Index: 405

Text #7

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9833. Min Act: -0.1700

Data Index: 2692290 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9771. Min Act: -0.1700

Data Index: 4379892 (Open Web Text)

Max Activating Token Index: 522

Text #9

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9803. Min Act: -0.1700

Data Index: 858048 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9934. Min Act: -0.1700

Data Index: 3091143 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9716. Min Act: -0.1700

Data Index: 2692291 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9714. Min Act: -0.1700

Data Index: 5619099 (Open Web Text)

Max Activating Token Index: 406

Text #13

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9798. Min Act: -0.1700

Data Index: 5223369 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9812. Min Act: -0.1700

Data Index: 803509 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9687. Min Act: -0.1700

Data Index: 6195197 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9593. Min Act: -0.1700

Data Index: 1247524 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9508. Min Act: -0.1700

Data Index: 6141729 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9612. Min Act: -0.1700

Data Index: 112497 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 2.1016. Min Range: -2.1016

Max Act: 1.9487. Min Act: -0.1700

Data Index: 4290532 (Open Web Text)

Max Activating Token Index: 456