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

Dataset: Open Web Text

Neuron 709 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: 3.1207. Min Range: -3.1207

Max Act: 3.1207. Min Act: -0.1700

Data Index: 6602014 (Open Web Text)

Max Activating Token Index: 190

Text #1

Max Range: 3.1207. Min Range: -3.1207

Max Act: 3.0982. Min Act: -0.1700

Data Index: 4238065 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 3.1207. Min Range: -3.1207

Max Act: 3.0613. Min Act: -0.1700

Data Index: 5854365 (Open Web Text)

Max Activating Token Index: 822

Text #3

Max Range: 3.1207. Min Range: -3.1207

Max Act: 3.0463. Min Act: -0.1700

Data Index: 1166408 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 3.1207. Min Range: -3.1207

Max Act: 3.0424. Min Act: -0.1700

Data Index: 6568320 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 3.1207. Min Range: -3.1207

Max Act: 3.0040. Min Act: -0.1700

Data Index: 3847850 (Open Web Text)

Max Activating Token Index: 694

Text #6

Max Range: 3.1207. Min Range: -3.1207

Max Act: 3.0194. Min Act: -0.1700

Data Index: 6967840 (Open Web Text)

Max Activating Token Index: 818

Text #7

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9726. Min Act: -0.1700

Data Index: 4629874 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9967. Min Act: -0.1700

Data Index: 2555359 (Open Web Text)

Max Activating Token Index: 440

Text #9

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9923. Min Act: -0.1700

Data Index: 3638231 (Open Web Text)

Max Activating Token Index: 99

Text #10

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9660. Min Act: -0.1700

Data Index: 5161151 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9573. Min Act: -0.1700

Data Index: 3050083 (Open Web Text)

Max Activating Token Index: 974

Text #12

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9454. Min Act: -0.1700

Data Index: 4306500 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9658. Min Act: -0.1700

Data Index: 8813508 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9474. Min Act: -0.1700

Data Index: 414810 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9365. Min Act: -0.1700

Data Index: 4395515 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9529. Min Act: -0.1700

Data Index: 6354657 (Open Web Text)

Max Activating Token Index: 296

Text #17

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9457. Min Act: -0.1700

Data Index: 840907 (Open Web Text)

Max Activating Token Index: 278

Text #18

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9330. Min Act: -0.1700

Data Index: 5589567 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 3.1207. Min Range: -3.1207

Max Act: 2.9447. Min Act: -0.1700

Data Index: 6300205 (Open Web Text)

Max Activating Token Index: 668