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

Dataset: Open Web Text

Neuron 1885 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: 4.5223. Min Range: -4.5223

Max Act: 4.5223. Min Act: -0.1700

Data Index: 7203498 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3939. Min Act: -0.1700

Data Index: 1502022 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3709. Min Act: -0.1700

Data Index: 5852972 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3783. Min Act: -0.1700

Data Index: 4378733 (Open Web Text)

Max Activating Token Index: 189

Text #4

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3559. Min Act: -0.1700

Data Index: 3601245 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3643. Min Act: -0.1700

Data Index: 1469690 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3473. Min Act: -0.1700

Data Index: 1009249 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3458. Min Act: -0.1700

Data Index: 5303030 (Open Web Text)

Max Activating Token Index: 549

Text #8

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3062. Min Act: -0.1700

Data Index: 1925625 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3413. Min Act: -0.1700

Data Index: 7322649 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3177. Min Act: -0.1700

Data Index: 1597752 (Open Web Text)

Max Activating Token Index: 235

Text #11

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3259. Min Act: -0.1700

Data Index: 514271 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3175. Min Act: -0.1700

Data Index: 6951628 (Open Web Text)

Max Activating Token Index: 596

Text #13

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3376. Min Act: -0.1700

Data Index: 6849895 (Open Web Text)

Max Activating Token Index: 852

Text #14

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3187. Min Act: -0.1700

Data Index: 6696068 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.2956. Min Act: -0.1700

Data Index: 3295982 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3090. Min Act: -0.1700

Data Index: 6298236 (Open Web Text)

Max Activating Token Index: 879

Text #17

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3227. Min Act: -0.1700

Data Index: 326523 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3265. Min Act: -0.1700

Data Index: 856892 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 4.5223. Min Range: -4.5223

Max Act: 4.3090. Min Act: -0.1700

Data Index: 5940264 (Open Web Text)

Max Activating Token Index: 422