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

Dataset: Open Web Text

Neuron 2280 in Layer 3

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: 3.3809. Min Range: -3.3809

Max Act: 3.3809. Min Act: -0.1700

Data Index: 4045508 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2871. Min Act: -0.1700

Data Index: 4332086 (Open Web Text)

Max Activating Token Index: 276

Text #2

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2736. Min Act: -0.1700

Data Index: 7423187 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2727. Min Act: -0.1700

Data Index: 8390269 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2499. Min Act: -0.1700

Data Index: 4322262 (Open Web Text)

Max Activating Token Index: 414

Text #5

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2557. Min Act: -0.1700

Data Index: 6835475 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2516. Min Act: -0.1700

Data Index: 1249746 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2288. Min Act: -0.1700

Data Index: 2971684 (Open Web Text)

Max Activating Token Index: 245

Text #8

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2348. Min Act: -0.1700

Data Index: 5703343 (Open Web Text)

Max Activating Token Index: 522

Text #9

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2431. Min Act: -0.1700

Data Index: 402479 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2337. Min Act: -0.1700

Data Index: 5779033 (Open Web Text)

Max Activating Token Index: 491

Text #11

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2428. Min Act: -0.1700

Data Index: 2458769 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2256. Min Act: -0.1700

Data Index: 7782495 (Open Web Text)

Max Activating Token Index: 879

Text #13

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2147. Min Act: -0.1700

Data Index: 280882 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2206. Min Act: -0.1700

Data Index: 260256 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2218. Min Act: -0.1700

Data Index: 8261110 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2197. Min Act: -0.1700

Data Index: 1599890 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2222. Min Act: -0.1700

Data Index: 3108842 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2272. Min Act: -0.1700

Data Index: 4621008 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 3.3809. Min Range: -3.3809

Max Act: 3.2252. Min Act: -0.1700

Data Index: 531559 (Open Web Text)

Max Activating Token Index: 503