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

Dataset: Open Web Text

Neuron 1027 in Layer 2

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: 4.4709. Min Range: -4.4709

Max Act: 4.4709. Min Act: -0.1700

Data Index: 4234190 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4445. Min Act: -0.1700

Data Index: 6960796 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4113. Min Act: -0.1700

Data Index: 2421120 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4240. Min Act: -0.1700

Data Index: 2880113 (Open Web Text)

Max Activating Token Index: 336

Text #4

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4111. Min Act: -0.1700

Data Index: 2014351 (Open Web Text)

Max Activating Token Index: 308

Text #5

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3895. Min Act: -0.1700

Data Index: 3240175 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3952. Min Act: -0.1700

Data Index: 367942 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4036. Min Act: -0.1700

Data Index: 3887908 (Open Web Text)

Max Activating Token Index: 552

Text #8

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4073. Min Act: -0.1700

Data Index: 8343207 (Open Web Text)

Max Activating Token Index: 919

Text #9

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4106. Min Act: -0.1700

Data Index: 5388978 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3977. Min Act: -0.1700

Data Index: 3358448 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.4082. Min Act: -0.1700

Data Index: 7743990 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3774. Min Act: -0.1700

Data Index: 2552970 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3688. Min Act: -0.1700

Data Index: 6486308 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3630. Min Act: -0.1700

Data Index: 320106 (Open Web Text)

Max Activating Token Index: 122

Text #15

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3642. Min Act: -0.1700

Data Index: 5311777 (Open Web Text)

Max Activating Token Index: 631

Text #16

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3878. Min Act: -0.1700

Data Index: 5437494 (Open Web Text)

Max Activating Token Index: 731

Text #17

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3809. Min Act: -0.1700

Data Index: 2552972 (Open Web Text)

Max Activating Token Index: 924

Text #18

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3770. Min Act: -0.1700

Data Index: 5285026 (Open Web Text)

Max Activating Token Index: 306

Text #19

Max Range: 4.4709. Min Range: -4.4709

Max Act: 4.3349. Min Act: -0.1700

Data Index: 6508436 (Open Web Text)

Max Activating Token Index: 469