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

Dataset: Open Web Text

Neuron 609 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: 3.8463. Min Range: -3.8463

Max Act: 3.8463. Min Act: -0.1700

Data Index: 6124874 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.7156. Min Act: -0.1700

Data Index: 2094418 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.7148. Min Act: -0.1700

Data Index: 7365814 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6837. Min Act: -0.1700

Data Index: 5534405 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1167217 (Open Web Text)

Max Activating Token Index: 285

Text #5

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6506. Min Act: -0.1700

Data Index: 7251318 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6433. Min Act: -0.1700

Data Index: 1888963 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6599. Min Act: -0.1700

Data Index: 7706802 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6324. Min Act: -0.1700

Data Index: 4838453 (Open Web Text)

Max Activating Token Index: 741

Text #9

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5852. Min Act: -0.1700

Data Index: 1207195 (Open Web Text)

Max Activating Token Index: 218

Text #10

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6263. Min Act: -0.1700

Data Index: 855351 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5982. Min Act: -0.1700

Data Index: 6771374 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5914. Min Act: -0.1700

Data Index: 4656292 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5982. Min Act: -0.1700

Data Index: 3319120 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5795. Min Act: -0.1700

Data Index: 7722140 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.6147. Min Act: -0.1700

Data Index: 7467640 (Open Web Text)

Max Activating Token Index: 818

Text #16

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5705. Min Act: -0.1700

Data Index: 5068853 (Open Web Text)

Max Activating Token Index: 568

Text #17

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5644. Min Act: -0.1700

Data Index: 2085883 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5649. Min Act: -0.1700

Data Index: 1210325 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 3.8463. Min Range: -3.8463

Max Act: 3.5739. Min Act: -0.1700

Data Index: 2364806 (Open Web Text)

Max Activating Token Index: 310