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

Dataset: Open Web Text

Neuron 2206 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: 2.5568. Min Range: -2.5568

Max Act: 2.5568. Min Act: -0.1700

Data Index: 8070474 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5340. Min Act: -0.1700

Data Index: 3488939 (Open Web Text)

Max Activating Token Index: 762

Text #2

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5368. Min Act: -0.1700

Data Index: 1864161 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5307. Min Act: -0.1700

Data Index: 981184 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5257. Min Act: -0.1700

Data Index: 6646193 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5368. Min Act: -0.1700

Data Index: 7866398 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5123. Min Act: -0.1700

Data Index: 8785372 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5363. Min Act: -0.1700

Data Index: 7378356 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.5057. Min Act: -0.1700

Data Index: 1098290 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4724. Min Act: -0.1700

Data Index: 930540 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4853. Min Act: -0.1700

Data Index: 281816 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4853. Min Act: -0.1700

Data Index: 482423 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4864. Min Act: -0.1700

Data Index: 966292 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4789. Min Act: -0.1700

Data Index: 5078700 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4872. Min Act: -0.1700

Data Index: 3061545 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4853. Min Act: -0.1700

Data Index: 8813316 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4853. Min Act: -0.1700

Data Index: 893992 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4853. Min Act: -0.1700

Data Index: 5767407 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4846. Min Act: -0.1700

Data Index: 7074843 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.5568. Min Range: -2.5568

Max Act: 2.4608. Min Act: -0.1700

Data Index: 8231987 (Open Web Text)

Max Activating Token Index: 12