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

Dataset: Open Web Text

Neuron 2750 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: 1.6235. Min Range: -1.6235

Max Act: 1.6235. Min Act: -0.1666

Data Index: 3821001 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.6030. Min Act: -0.0631

Data Index: 3694299 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5667. Min Act: -0.1498

Data Index: 3604855 (Open Web Text)

Max Activating Token Index: 442

Text #3

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5621. Min Act: -0.1366

Data Index: 6539020 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5611. Min Act: -0.0947

Data Index: 7597605 (Open Web Text)

Max Activating Token Index: 806

Text #5

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5595. Min Act: -0.0659

Data Index: 1870059 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5583. Min Act: -0.0953

Data Index: 6211779 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5425. Min Act: -0.0991

Data Index: 4175768 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5474. Min Act: -0.1058

Data Index: 803243 (Open Web Text)

Max Activating Token Index: 309

Text #9

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5464. Min Act: -0.1271

Data Index: 5857773 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5497. Min Act: -0.0398

Data Index: 5844882 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5418. Min Act: -0.0553

Data Index: 6949076 (Open Web Text)

Max Activating Token Index: 693

Text #12

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5373. Min Act: -0.0843

Data Index: 8703269 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5323. Min Act: -0.1316

Data Index: 7874505 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5299. Min Act: -0.1433

Data Index: 3727974 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5255. Min Act: -0.0841

Data Index: 3161638 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5301. Min Act: -0.1102

Data Index: 1821148 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5332. Min Act: -0.0944

Data Index: 2755948 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5352. Min Act: -0.1629

Data Index: 7424537 (Open Web Text)

Max Activating Token Index: 455

Text #19

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5288. Min Act: -0.1653

Data Index: 1745381 (Open Web Text)

Max Activating Token Index: 321