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

Dataset: Open Web Text

Neuron 2460 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: 5.2454. Min Range: -5.2454

Max Act: 5.2454. Min Act: -0.1700

Data Index: 1622774 (Open Web Text)

Max Activating Token Index: 444

Text #1

Max Range: 5.2454. Min Range: -5.2454

Max Act: 5.1332. Min Act: -0.1700

Data Index: 2729229 (Open Web Text)

Max Activating Token Index: 814

Text #2

Max Range: 5.2454. Min Range: -5.2454

Max Act: 5.0372. Min Act: -0.1700

Data Index: 1288101 (Open Web Text)

Max Activating Token Index: 262

Text #3

Max Range: 5.2454. Min Range: -5.2454

Max Act: 5.0199. Min Act: -0.1700

Data Index: 4221581 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 5.2454. Min Range: -5.2454

Max Act: 5.0437. Min Act: -0.1700

Data Index: 323160 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9903. Min Act: -0.1700

Data Index: 770310 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9620. Min Act: -0.1700

Data Index: 2509658 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9708. Min Act: -0.1700

Data Index: 5303344 (Open Web Text)

Max Activating Token Index: 857

Text #8

Max Range: 5.2454. Min Range: -5.2454

Max Act: 5.0106. Min Act: -0.1700

Data Index: 3390798 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 5.2454. Min Range: -5.2454

Max Act: 5.0034. Min Act: -0.1700

Data Index: 6970585 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9958. Min Act: -0.1700

Data Index: 6233681 (Open Web Text)

Max Activating Token Index: 438

Text #11

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9177. Min Act: -0.1700

Data Index: 7358088 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9492. Min Act: -0.1700

Data Index: 8404387 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9430. Min Act: -0.1700

Data Index: 8682346 (Open Web Text)

Max Activating Token Index: 772

Text #14

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9194. Min Act: -0.1700

Data Index: 2059974 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.8982. Min Act: -0.1700

Data Index: 139997 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.8928. Min Act: -0.1700

Data Index: 1972030 (Open Web Text)

Max Activating Token Index: 457

Text #17

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9417. Min Act: -0.1700

Data Index: 6583652 (Open Web Text)

Max Activating Token Index: 936

Text #18

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.8946. Min Act: -0.1700

Data Index: 354353 (Open Web Text)

Max Activating Token Index: 968

Text #19

Max Range: 5.2454. Min Range: -5.2454

Max Act: 4.9170. Min Act: -0.1700

Data Index: 5976813 (Open Web Text)

Max Activating Token Index: 589