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

Dataset: Open Web Text

Neuron 2617 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: 5.8260. Min Range: -5.8260

Max Act: 5.8260. Min Act: -0.1700

Data Index: 7562 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.3079. Min Act: -0.1700

Data Index: 8553997 (Open Web Text)

Max Activating Token Index: 267

Text #2

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.3799. Min Act: -0.1700

Data Index: 6519044 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.2662. Min Act: -0.1700

Data Index: 2762504 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.3545. Min Act: -0.1700

Data Index: 6343669 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1318. Min Act: -0.1700

Data Index: 1737150 (Open Web Text)

Max Activating Token Index: 996

Text #6

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.2772. Min Act: -0.1700

Data Index: 3504013 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1892. Min Act: -0.1700

Data Index: 4095127 (Open Web Text)

Max Activating Token Index: 699

Text #8

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1909. Min Act: -0.1700

Data Index: 644223 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.2147. Min Act: -0.1700

Data Index: 5609588 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.2778. Min Act: -0.1700

Data Index: 4328431 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.2603. Min Act: -0.1700

Data Index: 303460 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1567. Min Act: -0.1700

Data Index: 2333090 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1464. Min Act: -0.1700

Data Index: 8633185 (Open Web Text)

Max Activating Token Index: 387

Text #14

Max Range: 5.8260. Min Range: -5.8260

Max Act: 4.9748. Min Act: -0.1700

Data Index: 1868801 (Open Web Text)

Max Activating Token Index: 436

Text #15

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.0864. Min Act: -0.1700

Data Index: 8406966 (Open Web Text)

Max Activating Token Index: 535

Text #16

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1839. Min Act: -0.1700

Data Index: 4047945 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1425. Min Act: -0.1700

Data Index: 4828503 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1689. Min Act: -0.1700

Data Index: 2796364 (Open Web Text)

Max Activating Token Index: 959

Text #19

Max Range: 5.8260. Min Range: -5.8260

Max Act: 5.1527. Min Act: -0.1700

Data Index: 2548755 (Open Web Text)

Max Activating Token Index: 826