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

Dataset: Open Web Text

Neuron 2674 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: 3.0613. Min Range: -3.0613

Max Act: 3.0613. Min Act: -0.1700

Data Index: 7081136 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0551. Min Act: -0.1700

Data Index: 3330771 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0388. Min Act: -0.1700

Data Index: 1242102 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0136. Min Act: -0.1700

Data Index: 8082079 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0130. Min Act: -0.1700

Data Index: 5109504 (Open Web Text)

Max Activating Token Index: 231

Text #5

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0248. Min Act: -0.1700

Data Index: 2225498 (Open Web Text)

Max Activating Token Index: 428

Text #6

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0027. Min Act: -0.1700

Data Index: 7673278 (Open Web Text)

Max Activating Token Index: 683

Text #7

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9826. Min Act: -0.1700

Data Index: 2019845 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9740. Min Act: -0.1700

Data Index: 1490584 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9933. Min Act: -0.1700

Data Index: 7732196 (Open Web Text)

Max Activating Token Index: 359

Text #10

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9313. Min Act: -0.1700

Data Index: 7072666 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9371. Min Act: -0.1700

Data Index: 8440252 (Open Web Text)

Max Activating Token Index: 497

Text #12

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9396. Min Act: -0.1700

Data Index: 8428628 (Open Web Text)

Max Activating Token Index: 654

Text #13

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9176. Min Act: -0.1700

Data Index: 660770 (Open Web Text)

Max Activating Token Index: 250

Text #14

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9278. Min Act: -0.1700

Data Index: 2427086 (Open Web Text)

Max Activating Token Index: 732

Text #15

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9313. Min Act: -0.1700

Data Index: 7244801 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9231. Min Act: -0.1700

Data Index: 502740 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9253. Min Act: -0.1700

Data Index: 2914313 (Open Web Text)

Max Activating Token Index: 185

Text #18

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9073. Min Act: -0.1700

Data Index: 7782484 (Open Web Text)

Max Activating Token Index: 621

Text #19

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9035. Min Act: -0.1700

Data Index: 450675 (Open Web Text)

Max Activating Token Index: 505