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

Dataset: Open Web Text

Neuron 276 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: 1.3807. Min Range: -1.3807

Max Act: 1.3807. Min Act: -0.0602

Data Index: 442559 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3619. Min Act: -0.1040

Data Index: 2531012 (Open Web Text)

Max Activating Token Index: 400

Text #2

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3592. Min Act: -0.0756

Data Index: 1420403 (Open Web Text)

Max Activating Token Index: 259

Text #3

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3530. Min Act: -0.0823

Data Index: 6060709 (Open Web Text)

Max Activating Token Index: 396

Text #4

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3492. Min Act: -0.0670

Data Index: 5107930 (Open Web Text)

Max Activating Token Index: 336

Text #5

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3563. Min Act: -0.0602

Data Index: 2002868 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3545. Min Act: -0.1052

Data Index: 2495189 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3511. Min Act: -0.1149

Data Index: 2204935 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3588. Min Act: -0.0920

Data Index: 4468937 (Open Web Text)

Max Activating Token Index: 233

Text #9

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3503. Min Act: -0.0716

Data Index: 4010918 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3525. Min Act: -0.0855

Data Index: 7168937 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3556. Min Act: -0.0602

Data Index: 6296374 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3471. Min Act: -0.0602

Data Index: 7745126 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3436. Min Act: -0.0620

Data Index: 7790935 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3440. Min Act: -0.0788

Data Index: 3576426 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3494. Min Act: -0.0953

Data Index: 431529 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3418. Min Act: -0.0602

Data Index: 5275284 (Open Web Text)

Max Activating Token Index: 401

Text #17

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3370. Min Act: -0.0697

Data Index: 3759901 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3430. Min Act: -0.0602

Data Index: 4757876 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 1.3807. Min Range: -1.3807

Max Act: 1.3350. Min Act: -0.0785

Data Index: 439228 (Open Web Text)

Max Activating Token Index: 229