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

Dataset: Open Web Text

Neuron 2568 in Layer 1

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: 3.0842. Min Range: -3.0842

Max Act: 3.0842. Min Act: -0.1700

Data Index: 5878603 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0456. Min Act: -0.1700

Data Index: 5529410 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0012. Min Act: -0.1700

Data Index: 5005079 (Open Web Text)

Max Activating Token Index: 129

Text #3

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9916. Min Act: -0.1700

Data Index: 3394910 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9892. Min Act: -0.1700

Data Index: 7745113 (Open Web Text)

Max Activating Token Index: 478

Text #5

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9493. Min Act: -0.1698

Data Index: 6297264 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9286. Min Act: -0.1700

Data Index: 1182539 (Open Web Text)

Max Activating Token Index: 905

Text #7

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9020. Min Act: -0.1700

Data Index: 6367320 (Open Web Text)

Max Activating Token Index: 312

Text #8

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9287. Min Act: -0.1700

Data Index: 4106010 (Open Web Text)

Max Activating Token Index: 488

Text #9

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8617. Min Act: -0.1700

Data Index: 4369323 (Open Web Text)

Max Activating Token Index: 251

Text #10

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8702. Min Act: -0.1700

Data Index: 2232803 (Open Web Text)

Max Activating Token Index: 846

Text #11

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8644. Min Act: -0.1700

Data Index: 1793395 (Open Web Text)

Max Activating Token Index: 275

Text #12

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8325. Min Act: -0.1700

Data Index: 3585272 (Open Web Text)

Max Activating Token Index: 87

Text #13

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8359. Min Act: -0.1700

Data Index: 7740986 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8368. Min Act: -0.1700

Data Index: 6927619 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8319. Min Act: -0.1700

Data Index: 6671540 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8222. Min Act: -0.1700

Data Index: 2803795 (Open Web Text)

Max Activating Token Index: 773

Text #17

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8322. Min Act: -0.1700

Data Index: 3763480 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.8387. Min Act: -0.1700

Data Index: 1238929 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.7528. Min Act: -0.1700

Data Index: 2337813 (Open Web Text)

Max Activating Token Index: 688