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

Dataset: Open Web Text

Neuron 923 in Layer 5

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: 4.7425. Min Range: -4.7425

Max Act: 4.7425. Min Act: -0.1700

Data Index: 7373315 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6548. Min Act: -0.1700

Data Index: 8205249 (Open Web Text)

Max Activating Token Index: 574

Text #2

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6243. Min Act: -0.1700

Data Index: 5650332 (Open Web Text)

Max Activating Token Index: 374

Text #3

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6143. Min Act: -0.1700

Data Index: 1051586 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6030. Min Act: -0.1700

Data Index: 4558387 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6694. Min Act: -0.1700

Data Index: 7373311 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6007. Min Act: -0.1700

Data Index: 7373316 (Open Web Text)

Max Activating Token Index: 404

Text #7

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5813. Min Act: -0.1700

Data Index: 4187901 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5967. Min Act: -0.1700

Data Index: 3613540 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.6207. Min Act: -0.1700

Data Index: 1616180 (Open Web Text)

Max Activating Token Index: 693

Text #10

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5247. Min Act: -0.1700

Data Index: 5785383 (Open Web Text)

Max Activating Token Index: 718

Text #11

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5315. Min Act: -0.1700

Data Index: 4041454 (Open Web Text)

Max Activating Token Index: 794

Text #12

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5454. Min Act: -0.1700

Data Index: 6267290 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5490. Min Act: -0.1700

Data Index: 6686487 (Open Web Text)

Max Activating Token Index: 907

Text #14

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5193. Min Act: -0.1700

Data Index: 5176246 (Open Web Text)

Max Activating Token Index: 480

Text #15

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.5082. Min Act: -0.1700

Data Index: 3540622 (Open Web Text)

Max Activating Token Index: 842

Text #16

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.4741. Min Act: -0.1700

Data Index: 2426168 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.4926. Min Act: -0.1700

Data Index: 6294539 (Open Web Text)

Max Activating Token Index: 932

Text #18

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.4766. Min Act: -0.1700

Data Index: 4914228 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.4869. Min Act: -0.1700

Data Index: 5663410 (Open Web Text)

Max Activating Token Index: 281