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

Dataset: Open Web Text

Neuron 886 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: 3.6863. Min Range: -3.6863

Max Act: 3.6863. Min Act: -0.1700

Data Index: 2895558 (Open Web Text)

Max Activating Token Index: 822

Text #1

Max Range: 3.6863. Min Range: -3.6863

Max Act: 3.4178. Min Act: -0.1700

Data Index: 5693912 (Open Web Text)

Max Activating Token Index: 87

Text #2

Max Range: 3.6863. Min Range: -3.6863

Max Act: 3.0536. Min Act: -0.1700

Data Index: 8375289 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 3.6863. Min Range: -3.6863

Max Act: 3.0571. Min Act: -0.1700

Data Index: 8012697 (Open Web Text)

Max Activating Token Index: 763

Text #4

Max Range: 3.6863. Min Range: -3.6863

Max Act: 3.0297. Min Act: -0.1700

Data Index: 379503 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 3.6863. Min Range: -3.6863

Max Act: 3.0243. Min Act: -0.1700

Data Index: 7326422 (Open Web Text)

Max Activating Token Index: 739

Text #6

Max Range: 3.6863. Min Range: -3.6863

Max Act: 3.0162. Min Act: -0.1700

Data Index: 8592895 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9863. Min Act: -0.1700

Data Index: 3356778 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9394. Min Act: -0.1700

Data Index: 5669840 (Open Web Text)

Max Activating Token Index: 709

Text #9

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9430. Min Act: -0.1700

Data Index: 1183774 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9358. Min Act: -0.1700

Data Index: 4209493 (Open Web Text)

Max Activating Token Index: 550

Text #11

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9646. Min Act: -0.1700

Data Index: 6797988 (Open Web Text)

Max Activating Token Index: 243

Text #12

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9481. Min Act: -0.1700

Data Index: 2329687 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9349. Min Act: -0.1700

Data Index: 7169346 (Open Web Text)

Max Activating Token Index: 266

Text #14

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9466. Min Act: -0.1700

Data Index: 2559948 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.8806. Min Act: -0.1700

Data Index: 6389741 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.8944. Min Act: -0.1700

Data Index: 5156899 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.8660. Min Act: -0.1700

Data Index: 3189318 (Open Web Text)

Max Activating Token Index: 161

Text #18

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.8873. Min Act: -0.1700

Data Index: 735736 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 3.6863. Min Range: -3.6863

Max Act: 2.9115. Min Act: -0.1700

Data Index: 5438546 (Open Web Text)

Max Activating Token Index: 771