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

Dataset: Open Web Text

Neuron 1070 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: 5.0414. Min Range: -5.0414

Max Act: 5.0414. Min Act: -0.1700

Data Index: 8655238 (Open Web Text)

Max Activating Token Index: 685

Text #1

Max Range: 5.0414. Min Range: -5.0414

Max Act: 5.0258. Min Act: -0.1700

Data Index: 6171796 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.9997. Min Act: -0.1700

Data Index: 2144962 (Open Web Text)

Max Activating Token Index: 49

Text #3

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.9998. Min Act: -0.1700

Data Index: 6141742 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.9634. Min Act: -0.1700

Data Index: 7777866 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.9459. Min Act: -0.1700

Data Index: 3696766 (Open Web Text)

Max Activating Token Index: 129

Text #6

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8921. Min Act: -0.1700

Data Index: 7990035 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.9466. Min Act: -0.1700

Data Index: 1668375 (Open Web Text)

Max Activating Token Index: 795

Text #8

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.9089. Min Act: -0.1700

Data Index: 807571 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8309. Min Act: -0.1700

Data Index: 3945385 (Open Web Text)

Max Activating Token Index: 920

Text #10

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8783. Min Act: -0.1700

Data Index: 719073 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8864. Min Act: -0.1700

Data Index: 6129 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8474. Min Act: -0.1700

Data Index: 8786711 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8692. Min Act: -0.1700

Data Index: 6276605 (Open Web Text)

Max Activating Token Index: 286

Text #14

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8357. Min Act: -0.1700

Data Index: 5705346 (Open Web Text)

Max Activating Token Index: 739

Text #15

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8062. Min Act: -0.1700

Data Index: 6287953 (Open Web Text)

Max Activating Token Index: 934

Text #16

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8283. Min Act: -0.1700

Data Index: 753973 (Open Web Text)

Max Activating Token Index: 755

Text #17

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.8372. Min Act: -0.1700

Data Index: 2788207 (Open Web Text)

Max Activating Token Index: 548

Text #18

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.7811. Min Act: -0.1700

Data Index: 5040978 (Open Web Text)

Max Activating Token Index: 549

Text #19

Max Range: 5.0414. Min Range: -5.0414

Max Act: 4.7999. Min Act: -0.1700

Data Index: 3662335 (Open Web Text)

Max Activating Token Index: 346