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

Dataset: Open Web Text

Neuron 2706 in Layer 2

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: 2.2911. Min Range: -2.2911

Max Act: 2.2911. Min Act: -0.1700

Data Index: 6588813 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2644. Min Act: -0.1700

Data Index: 2847749 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2549. Min Act: -0.1700

Data Index: 6531162 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2238. Min Act: -0.1700

Data Index: 4018669 (Open Web Text)

Max Activating Token Index: 374

Text #4

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2182. Min Act: -0.1700

Data Index: 4302001 (Open Web Text)

Max Activating Token Index: 105

Text #5

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2335. Min Act: -0.1700

Data Index: 4056439 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2112. Min Act: -0.1700

Data Index: 4963814 (Open Web Text)

Max Activating Token Index: 537

Text #7

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2199. Min Act: -0.1700

Data Index: 3355829 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2077. Min Act: -0.1700

Data Index: 6018067 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.2116. Min Act: -0.1700

Data Index: 538224 (Open Web Text)

Max Activating Token Index: 640

Text #10

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1788. Min Act: -0.1700

Data Index: 2042048 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1688. Min Act: -0.1700

Data Index: 3532490 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1646. Min Act: -0.1700

Data Index: 5195895 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1799. Min Act: -0.1700

Data Index: 5509291 (Open Web Text)

Max Activating Token Index: 585

Text #14

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1711. Min Act: -0.1700

Data Index: 538219 (Open Web Text)

Max Activating Token Index: 921

Text #15

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1581. Min Act: -0.1700

Data Index: 8469859 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1493. Min Act: -0.1700

Data Index: 6680747 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1603. Min Act: -0.1700

Data Index: 4324024 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1653. Min Act: -0.1700

Data Index: 1662161 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 2.2911. Min Range: -2.2911

Max Act: 2.1485. Min Act: -0.1700

Data Index: 4792862 (Open Web Text)

Max Activating Token Index: 6