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

Dataset: Open Web Text

Neuron 972 in Layer 4

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: 4.8146. Min Range: -4.8146

Max Act: 4.7762. Min Act: -0.1700

Data Index: 2882585 (Open Web Text)

Max Activating Token Index: 302

Text #1

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.7957. Min Act: -0.1700

Data Index: 2219308 (Open Web Text)

Max Activating Token Index: 247

Text #2

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.8146. Min Act: -0.1700

Data Index: 2100020 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.7131. Min Act: -0.1700

Data Index: 1434765 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.7117. Min Act: -0.1700

Data Index: 7748487 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.6840. Min Act: -0.1700

Data Index: 5658669 (Open Web Text)

Max Activating Token Index: 934

Text #6

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.6822. Min Act: -0.1700

Data Index: 6884884 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.6750. Min Act: -0.1700

Data Index: 2571428 (Open Web Text)

Max Activating Token Index: 915

Text #8

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.7052. Min Act: -0.1700

Data Index: 7671821 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.6133. Min Act: -0.1700

Data Index: 7553096 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.6105. Min Act: -0.1700

Data Index: 2370710 (Open Web Text)

Max Activating Token Index: 204

Text #11

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5986. Min Act: -0.1700

Data Index: 8160644 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5176. Min Act: -0.1700

Data Index: 8585670 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5460. Min Act: -0.1700

Data Index: 4721000 (Open Web Text)

Max Activating Token Index: 280

Text #14

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5377. Min Act: -0.1700

Data Index: 6992594 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5448. Min Act: -0.1700

Data Index: 4411682 (Open Web Text)

Max Activating Token Index: 646

Text #16

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5434. Min Act: -0.1700

Data Index: 7607179 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5604. Min Act: -0.1700

Data Index: 8092377 (Open Web Text)

Max Activating Token Index: 350

Text #18

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.4980. Min Act: -0.1700

Data Index: 3535529 (Open Web Text)

Max Activating Token Index: 992

Text #19

Max Range: 4.8146. Min Range: -4.8146

Max Act: 4.5334. Min Act: -0.1700

Data Index: 1675971 (Open Web Text)

Max Activating Token Index: 257