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

Dataset: Open Web Text

Neuron 12 in Layer 5

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: 4.3120. Min Range: -4.3120

Max Act: 4.3120. Min Act: -0.1700

Data Index: 1507292 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.2717. Min Act: -0.1700

Data Index: 2310752 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.2410. Min Act: -0.1700

Data Index: 6609135 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.2081. Min Act: -0.1700

Data Index: 5963804 (Open Web Text)

Max Activating Token Index: 658

Text #4

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.2380. Min Act: -0.1700

Data Index: 5778642 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1785. Min Act: -0.1700

Data Index: 5236733 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1645. Min Act: -0.1700

Data Index: 541096 (Open Web Text)

Max Activating Token Index: 646

Text #7

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1600. Min Act: -0.1700

Data Index: 8600830 (Open Web Text)

Max Activating Token Index: 302

Text #8

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1348. Min Act: -0.1700

Data Index: 5427695 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1071. Min Act: -0.1700

Data Index: 8339334 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1073. Min Act: -0.1700

Data Index: 535529 (Open Web Text)

Max Activating Token Index: 812

Text #11

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1250. Min Act: -0.1700

Data Index: 6444072 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1218. Min Act: -0.1700

Data Index: 4911417 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1266. Min Act: -0.1700

Data Index: 4064230 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1027. Min Act: -0.1700

Data Index: 5736001 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1119. Min Act: -0.1700

Data Index: 26120 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.1167. Min Act: -0.1700

Data Index: 826582 (Open Web Text)

Max Activating Token Index: 643

Text #17

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.0952. Min Act: -0.1700

Data Index: 3589271 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.0875. Min Act: -0.1700

Data Index: 5515005 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 4.3120. Min Range: -4.3120

Max Act: 4.0961. Min Act: -0.1700

Data Index: 2747376 (Open Web Text)

Max Activating Token Index: 884