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

Dataset: Open Web Text

Neuron 1813 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: 1.9335. Min Range: -1.9335

Max Act: 1.9258. Min Act: -0.1283

Data Index: 1122230 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.9335. Min Act: -0.1283

Data Index: 8288091 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8764. Min Act: -0.1560

Data Index: 5152148 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8735. Min Act: -0.1283

Data Index: 1122208 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8436. Min Act: -0.1677

Data Index: 4167028 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8404. Min Act: -0.1411

Data Index: 8274364 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8340. Min Act: -0.1426

Data Index: 8274361 (Open Web Text)

Max Activating Token Index: 201

Text #7

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8261. Min Act: -0.1283

Data Index: 8274365 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8285. Min Act: -0.1554

Data Index: 8120821 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8231. Min Act: -0.1288

Data Index: 8274363 (Open Web Text)

Max Activating Token Index: 184

Text #10

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.8129. Min Act: -0.1283

Data Index: 8088463 (Open Web Text)

Max Activating Token Index: 290

Text #11

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7882. Min Act: -0.1390

Data Index: 8166711 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7798. Min Act: -0.1489

Data Index: 366070 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7741. Min Act: -0.1599

Data Index: 6281666 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7778. Min Act: -0.1515

Data Index: 4120559 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7698. Min Act: -0.1565

Data Index: 3138885 (Open Web Text)

Max Activating Token Index: 535

Text #16

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7465. Min Act: -0.1603

Data Index: 3680420 (Open Web Text)

Max Activating Token Index: 551

Text #17

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7500. Min Act: -0.1694

Data Index: 6670680 (Open Web Text)

Max Activating Token Index: 900

Text #18

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7456. Min Act: -0.1551

Data Index: 4397477 (Open Web Text)

Max Activating Token Index: 147

Text #19

Max Range: 1.9335. Min Range: -1.9335

Max Act: 1.7330. Min Act: -0.1562

Data Index: 7873268 (Open Web Text)

Max Activating Token Index: 525