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

Dataset: Open Web Text

Neuron 2006 in Layer 6

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: 6.3715. Min Range: -6.3715

Max Act: 6.3715. Min Act: -0.1700

Data Index: 6081157 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 6.3715. Min Range: -6.3715

Max Act: 6.0448. Min Act: -0.1700

Data Index: 7009800 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.9584. Min Act: -0.1700

Data Index: 4116972 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.9473. Min Act: -0.1700

Data Index: 8247333 (Open Web Text)

Max Activating Token Index: 67

Text #4

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.9067. Min Act: -0.1700

Data Index: 2536754 (Open Web Text)

Max Activating Token Index: 924

Text #5

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.9184. Min Act: -0.1700

Data Index: 3063322 (Open Web Text)

Max Activating Token Index: 713

Text #6

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.7224. Min Act: -0.1700

Data Index: 1500065 (Open Web Text)

Max Activating Token Index: 315

Text #7

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.7109. Min Act: -0.1700

Data Index: 7503999 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.6863. Min Act: -0.1700

Data Index: 4951950 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.6350. Min Act: -0.1700

Data Index: 6699047 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.6990. Min Act: -0.1700

Data Index: 5819100 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.6425. Min Act: -0.1700

Data Index: 576778 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.6231. Min Act: -0.1700

Data Index: 8521406 (Open Web Text)

Max Activating Token Index: 271

Text #13

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5967. Min Act: -0.1700

Data Index: 1885516 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5975. Min Act: -0.1700

Data Index: 7118930 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5714. Min Act: -0.1700

Data Index: 7810117 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5591. Min Act: -0.1700

Data Index: 1783835 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5510. Min Act: -0.1700

Data Index: 4287525 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5644. Min Act: -0.1700

Data Index: 6283471 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 6.3715. Min Range: -6.3715

Max Act: 5.5394. Min Act: -0.1700

Data Index: 3748012 (Open Web Text)

Max Activating Token Index: 482