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

Dataset: Open Web Text

Neuron 1244 in Layer 6

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: 6.2487. Min Range: -6.2487

Max Act: 6.2487. Min Act: -0.1700

Data Index: 5695029 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 6.2487. Min Range: -6.2487

Max Act: 6.1140. Min Act: -0.1700

Data Index: 6123580 (Open Web Text)

Max Activating Token Index: 259

Text #2

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.9841. Min Act: -0.1700

Data Index: 4513870 (Open Web Text)

Max Activating Token Index: 847

Text #3

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.8975. Min Act: -0.1700

Data Index: 1736127 (Open Web Text)

Max Activating Token Index: 524

Text #4

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.9317. Min Act: -0.1700

Data Index: 5518885 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.9260. Min Act: -0.1700

Data Index: 1394722 (Open Web Text)

Max Activating Token Index: 803

Text #6

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.8882. Min Act: -0.1700

Data Index: 5940364 (Open Web Text)

Max Activating Token Index: 761

Text #7

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.7827. Min Act: -0.1700

Data Index: 5347669 (Open Web Text)

Max Activating Token Index: 597

Text #8

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.7515. Min Act: -0.1700

Data Index: 8807522 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.7402. Min Act: -0.1700

Data Index: 1808730 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.7213. Min Act: -0.1700

Data Index: 4660460 (Open Web Text)

Max Activating Token Index: 640

Text #11

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.6777. Min Act: -0.1700

Data Index: 6053938 (Open Web Text)

Max Activating Token Index: 884

Text #12

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.6732. Min Act: -0.1700

Data Index: 1862959 (Open Web Text)

Max Activating Token Index: 578

Text #13

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.6469. Min Act: -0.1700

Data Index: 572397 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.6733. Min Act: -0.1700

Data Index: 7639483 (Open Web Text)

Max Activating Token Index: 855

Text #15

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.6332. Min Act: -0.1700

Data Index: 8288315 (Open Web Text)

Max Activating Token Index: 696

Text #16

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.6142. Min Act: -0.1700

Data Index: 4139942 (Open Web Text)

Max Activating Token Index: 342

Text #17

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.5135. Min Act: -0.1700

Data Index: 5672912 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.5310. Min Act: -0.1700

Data Index: 946638 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 6.2487. Min Range: -6.2487

Max Act: 5.5190. Min Act: -0.1700

Data Index: 1369624 (Open Web Text)

Max Activating Token Index: 899