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

Dataset: Open Web Text

Neuron 1721 in Layer 3

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: 4.1400. Min Range: -4.1400

Max Act: 4.1400. Min Act: -0.1700

Data Index: 1300272 (Open Web Text)

Max Activating Token Index: 389

Text #1

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.1246. Min Act: -0.1700

Data Index: 5081789 (Open Web Text)

Max Activating Token Index: 977

Text #2

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.1029. Min Act: -0.1700

Data Index: 2741897 (Open Web Text)

Max Activating Token Index: 172

Text #3

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0971. Min Act: -0.1700

Data Index: 5992260 (Open Web Text)

Max Activating Token Index: 209

Text #4

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0697. Min Act: -0.1700

Data Index: 2712354 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0698. Min Act: -0.1700

Data Index: 4462909 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0561. Min Act: -0.1700

Data Index: 8490975 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0347. Min Act: -0.1700

Data Index: 1051813 (Open Web Text)

Max Activating Token Index: 762

Text #8

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0322. Min Act: -0.1700

Data Index: 1136383 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0152. Min Act: -0.1700

Data Index: 8522493 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0021. Min Act: -0.1700

Data Index: 1628870 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 4.1400. Min Range: -4.1400

Max Act: 3.9969. Min Act: -0.1700

Data Index: 4363807 (Open Web Text)

Max Activating Token Index: 571

Text #12

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0235. Min Act: -0.1700

Data Index: 8684079 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0083. Min Act: -0.1700

Data Index: 3543813 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0088. Min Act: -0.1700

Data Index: 8514439 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 4.1400. Min Range: -4.1400

Max Act: 3.9914. Min Act: -0.1700

Data Index: 3073160 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.1400. Min Range: -4.1400

Max Act: 4.0130. Min Act: -0.1700

Data Index: 1310613 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 4.1400. Min Range: -4.1400

Max Act: 3.9890. Min Act: -0.1700

Data Index: 453381 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 4.1400. Min Range: -4.1400

Max Act: 3.9868. Min Act: -0.1700

Data Index: 4735412 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 4.1400. Min Range: -4.1400

Max Act: 3.9502. Min Act: -0.1700

Data Index: 5481705 (Open Web Text)

Max Activating Token Index: 241