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

Dataset: Open Web Text

Neuron 2298 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: 3.2310. Min Range: -3.2310

Max Act: 3.1993. Min Act: -0.1700

Data Index: 5279190 (Open Web Text)

Max Activating Token Index: 231

Text #1

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.2310. Min Act: -0.1700

Data Index: 6164536 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1720. Min Act: -0.1700

Data Index: 5838711 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1470. Min Act: -0.1700

Data Index: 1890295 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1556. Min Act: -0.1700

Data Index: 6806026 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1099. Min Act: -0.1700

Data Index: 3856799 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1228. Min Act: -0.1700

Data Index: 1891966 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.1009. Min Act: -0.1700

Data Index: 5659730 (Open Web Text)

Max Activating Token Index: 421

Text #8

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0994. Min Act: -0.1700

Data Index: 2206263 (Open Web Text)

Max Activating Token Index: 958

Text #9

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0915. Min Act: -0.1700

Data Index: 4146550 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0981. Min Act: -0.1700

Data Index: 1173848 (Open Web Text)

Max Activating Token Index: 659

Text #11

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0660. Min Act: -0.1700

Data Index: 7945873 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0781. Min Act: -0.1700

Data Index: 1238768 (Open Web Text)

Max Activating Token Index: 134

Text #13

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0792. Min Act: -0.1700

Data Index: 8590106 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0877. Min Act: -0.1700

Data Index: 6899948 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0834. Min Act: -0.1700

Data Index: 3486501 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0749. Min Act: -0.1700

Data Index: 3899140 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0755. Min Act: -0.1700

Data Index: 5522574 (Open Web Text)

Max Activating Token Index: 296

Text #18

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0659. Min Act: -0.1700

Data Index: 8209307 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 3.2310. Min Range: -3.2310

Max Act: 3.0158. Min Act: -0.1700

Data Index: 3599133 (Open Web Text)

Max Activating Token Index: 1008