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

Dataset: Open Web Text

Neuron 1196 in Layer 1

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: 1.8217. Min Range: -1.8217

Max Act: 1.8217. Min Act: -0.1700

Data Index: 5256718 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.8025. Min Act: -0.1699

Data Index: 8038379 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.8059. Min Act: -0.1699

Data Index: 8340844 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7881. Min Act: -0.1699

Data Index: 3293315 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7857. Min Act: -0.1700

Data Index: 2178068 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7821. Min Act: -0.1695

Data Index: 6889186 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7849. Min Act: -0.1699

Data Index: 6868711 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7875. Min Act: -0.1700

Data Index: 3009892 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7783. Min Act: -0.1700

Data Index: 6458307 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7713. Min Act: -0.1700

Data Index: 5709788 (Open Web Text)

Max Activating Token Index: 900

Text #10

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7702. Min Act: -0.1700

Data Index: 3443995 (Open Web Text)

Max Activating Token Index: 514

Text #11

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7760. Min Act: -0.1700

Data Index: 7967054 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7722. Min Act: -0.1698

Data Index: 4929884 (Open Web Text)

Max Activating Token Index: 665

Text #13

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7646. Min Act: -0.1700

Data Index: 8407873 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7649. Min Act: -0.1700

Data Index: 5689901 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7593. Min Act: -0.1700

Data Index: 2749092 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7532. Min Act: -0.1700

Data Index: 5932943 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7489. Min Act: -0.1699

Data Index: 7468031 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7526. Min Act: -0.1700

Data Index: 7191811 (Open Web Text)

Max Activating Token Index: 885

Text #19

Max Range: 1.8217. Min Range: -1.8217

Max Act: 1.7478. Min Act: -0.1700

Data Index: 7014456 (Open Web Text)

Max Activating Token Index: 266