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

Dataset: Open Web Text

Neuron 794 in Layer 0

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: 1.3257. Min Range: -1.3257

Max Act: 1.3257. Min Act: -0.1295

Data Index: 212960 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3213. Min Act: -0.1472

Data Index: 293775 (Open Web Text)

Max Activating Token Index: 519

Text #2

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3146. Min Act: -0.1195

Data Index: 4203081 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3142. Min Act: -0.1440

Data Index: 7760095 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3021. Min Act: -0.1599

Data Index: 5642694 (Open Web Text)

Max Activating Token Index: 77

Text #5

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3057. Min Act: -0.1388

Data Index: 4798210 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2965. Min Act: -0.1537

Data Index: 5831504 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2967. Min Act: -0.1405

Data Index: 6915736 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2883. Min Act: -0.1303

Data Index: 4396894 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2977. Min Act: -0.1366

Data Index: 6812196 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2982. Min Act: -0.1243

Data Index: 2669200 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2822. Min Act: -0.1401

Data Index: 1498137 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2788. Min Act: -0.1399

Data Index: 4760299 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2767. Min Act: -0.1414

Data Index: 4702288 (Open Web Text)

Max Activating Token Index: 511

Text #14

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2848. Min Act: -0.1300

Data Index: 3872753 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2860. Min Act: -0.1289

Data Index: 7402911 (Open Web Text)

Max Activating Token Index: 534

Text #16

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2795. Min Act: -0.1496

Data Index: 4247471 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2837. Min Act: -0.1417

Data Index: 6333660 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2835. Min Act: -0.1236

Data Index: 2646963 (Open Web Text)

Max Activating Token Index: 51

Text #19

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2822. Min Act: -0.1453

Data Index: 3994381 (Open Web Text)

Max Activating Token Index: 514