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

Dataset: Open Web Text

Neuron 1197 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: 1.6355. Min Range: -1.6355

Max Act: 1.6355. Min Act: -0.0179

Data Index: 5625840 (Open Web Text)

Max Activating Token Index: 537

Text #1

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.6111. Min Act: -0.1130

Data Index: 1888479 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.6109. Min Act: -0.0555

Data Index: 7263387 (Open Web Text)

Max Activating Token Index: 933

Text #3

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5972. Min Act: 0.0356

Data Index: 3422874 (Open Web Text)

Max Activating Token Index: 434

Text #4

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5889. Min Act: -0.0641

Data Index: 1691417 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5680. Min Act: -0.1165

Data Index: 3515316 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5712. Min Act: 0.0097

Data Index: 3569378 (Open Web Text)

Max Activating Token Index: 495

Text #7

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5745. Min Act: -0.0400

Data Index: 5674404 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5721. Min Act: -0.0242

Data Index: 1085460 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5712. Min Act: -0.0441

Data Index: 282795 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5743. Min Act: -0.0482

Data Index: 3474106 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5629. Min Act: -0.0449

Data Index: 292820 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5630. Min Act: -0.0509

Data Index: 5321754 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5509. Min Act: -0.0342

Data Index: 4630895 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5552. Min Act: -0.1103

Data Index: 8211837 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5499. Min Act: -0.0555

Data Index: 3209878 (Open Web Text)

Max Activating Token Index: 559

Text #16

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5530. Min Act: -0.0365

Data Index: 1780455 (Open Web Text)

Max Activating Token Index: 247

Text #17

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5458. Min Act: -0.0133

Data Index: 2261838 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5468. Min Act: -0.0301

Data Index: 875818 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 1.6355. Min Range: -1.6355

Max Act: 1.5502. Min Act: -0.0459

Data Index: 1284663 (Open Web Text)

Max Activating Token Index: 965